Search Results for author:
Found 177 papers, 100 papers with code
Memory Selection Network for Video Propagation
Video propagation is a fundamental problem in video processing where guidance frame predictions are propagated to guide predictions of the target frame.
Particularity beyond Commonality: Unpaired Identity Transfer with Multiple References
Unpaired image-to-image translation aims to translate images from the source class to target one by providing sufficient data for these classes.
CN: Channel Normalization For Point Cloud Recognition
In 3D recognition, to fuse multi-scale structure information, existing methods apply hierarchical frameworks stacked by multiple fusion layers for integrating current relative locations with structure information from the previous level.
Scalable Language Model with Generalized Continual Learning
In this study, we introduce the Scalable Language Model (SLM) to overcome these limitations within a more challenging and generalized setting, representing a significant advancement toward practical applications for continual learning.
Unified Language-driven Zero-shot Domain Adaptation
This paper introduces Unified Language-driven Zero-shot Domain Adaptation (ULDA), a novel task setting that enables a single model to adapt to diverse target domains without explicit domain-ID knowledge.
Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models
We try to narrow the gap by mining the potential of VLMs for better performance and any-to-any workflow from three aspects, i. e., high-resolution visual tokens, high-quality data, and VLM-guided generation.
Ranked #8 on
Visual Question Answering
on MM-Vet
OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation
This exploration led to the creation of Omni-Adaptive 3D CNNs (OA-CNNs), a family of networks that integrates a lightweight module to greatly enhance the adaptivity of sparse CNNs at minimal computational cost.
Ranked #5 on
3D Semantic Segmentation
on ScanNet200
GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding
To address this issue, we propose GroupContrast, a novel approach that combines segment grouping and semantic-aware contrastive learning.
RL-GPT: Integrating Reinforcement Learning and Code-as-policy
To seamlessly integrate both modalities, we introduce a two-level hierarchical framework, RL-GPT, comprising a slow agent and a fast agent.
VLPose: Bridging the Domain Gap in Pose Estimation with Language-Vision Tuning
Our research aims to bridge the domain gap between natural and artificial scenarios with efficient tuning strategies.
MOODv2: Masked Image Modeling for Out-of-Distribution Detection
The crux of effective out-of-distribution (OOD) detection lies in acquiring a robust in-distribution (ID) representation, distinct from OOD samples.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
MR-GSM8K: A Meta-Reasoning Revolution in Large Language Model Evaluation
In this work, we introduce a novel evaluation paradigm for Large Language Models, one that challenges them to engage in meta-reasoning.
LISA++: An Improved Baseline for Reasoning Segmentation with Large Language Model
While LISA effectively bridges the gap between segmentation and large language models to enable reasoning segmentation, it poses certain limitations: unable to distinguish different instances of the target region, and constrained by the pre-defined textual response formats.
BAL: Balancing Diversity and Novelty for Active Learning
Experimental results demonstrate that, when labeling 80% of the samples, the performance of the current SOTA method declines by 0. 74%, whereas our proposed BAL achieves performance comparable to the full dataset.
MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks
Large Language Models (LLMs) have showcased impressive capabilities in handling straightforward programming tasks.
Ranked #1 on
Code Generation
on CodeContests
(Test Set pass@1 metric)
Prompt Highlighter: Interactive Control for Multi-Modal LLMs
Without tuning on LLaVA-v1. 5, our method secured 70. 7 in the MMBench test and 1552. 5 in MME-perception.
LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models
Current VLMs, while proficient in tasks like image captioning and visual question answering, face computational burdens when processing long videos due to the excessive visual tokens.
Image Captioning
Video-based Generative Performance Benchmarking
+2
LLMGA: Multimodal Large Language Model based Generation Assistant
In the first stage, we train the MLLM to grasp the properties of image generation and editing, enabling it to generate detailed prompts.
Lightweight In-Context Tuning for Multimodal Unified Models
In-context learning (ICL) involves reasoning from given contextual examples.
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
For example, training on the context length of 8192 needs 16x computational costs in self-attention layers as that of 2048.
Mask-Attention-Free Transformer for 3D Instance Segmentation
Therefore, we abandon the mask attention design and resort to an auxiliary center regression task instead.
FocalFormer3D : Focusing on Hard Instance for 3D Object Detection
For 3D object detection, we instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall.
Ranked #8 on
3D Object Detection
on nuScenes
LISA: Reasoning Segmentation via Large Language Model
In this work, we propose a new segmentation task -- reasoning segmentation.
Hierarchical Dense Correlation Distillation for Few-Shot Segmentation-Extended Abstract
We hope our work can benefit broader industrial applications where novel classes with limited annotations are required to be decently identified.
Real-World Image Variation by Aligning Diffusion Inversion Chain
Our pipeline enhances the generation quality of image variations by aligning the image generation process to the source image's inversion chain.
Self-supervised Learning by View Synthesis
In each iteration, the input to VSA is one view (or multiple views) of a 3D object and the output is a synthesized image in another target pose.
TagCLIP: Improving Discrimination Ability of Open-Vocabulary Semantic Segmentation
However, existing models easily misidentify input pixels from unseen classes, thus confusing novel classes with semantically-similar ones.
Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields
Also, we present Point Encoding to build Multi-scale Radiance Fields that provide discriminative 3D point features.
TriVol: Point Cloud Rendering via Triple Volumes
However, artifacts still appear in rendered images, due to the challenges in extracting continuous and discriminative 3D features from point clouds.
Hierarchical Dense Correlation Distillation for Few-Shot Segmentation
Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations.
Ranked #6 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
Spherical Transformer for LiDAR-based 3D Recognition
In this work, we study the varying-sparsity distribution of LiDAR points and present SphereFormer to directly aggregate information from dense close points to the sparse distant ones.
Ranked #1 on
Semantic Segmentation
on KITTI Semantic Segmentation
Learning Context-aware Classifier for Semantic Segmentation
Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing.
VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking
Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies.
Ranked #1 on
3D Object Detection
on Argoverse2
Video-P2P: Video Editing with Cross-attention Control
This paper presents Video-P2P, a novel framework for real-world video editing with cross-attention control.
StraIT: Non-autoregressive Generation with Stratified Image Transformer
We propose Stratified Image Transformer(StraIT), a pure non-autoregressive(NAR) generative model that demonstrates superiority in high-quality image synthesis over existing autoregressive(AR) and diffusion models(DMs).
Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need
The core of out-of-distribution (OOD) detection is to learn the in-distribution (ID) representation, which is distinguishable from OOD samples.
Ranked #12 on
Out-of-Distribution Detection
on ImageNet-1k vs Places
(AUROC metric)
Understanding Imbalanced Semantic Segmentation Through Neural Collapse
Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers.
High Quality Entity Segmentation
Given the high-quality and -resolution nature of the dataset, we propose CropFormer which is designed to tackle the intractability of instance-level segmentation on high-resolution images.
End-to-end 3D Tracking with Decoupled Queries
In this work, we present an end-to-end framework for camera-based 3D multi-object tracking, called DQTrack.
FocalFormer3D: Focusing on Hard Instance for 3D Object Detection
For 3D object detection, we instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall.
Command-Driven Articulated Object Understanding and Manipulation
The key of Cart is to utilize the prediction of object structures to connect visual observations with user commands for effective manipulations.
Removing Anomalies as Noises for Industrial Defect Localization
Our denoising model outperforms the state-of-the-art reconstruction-based anomaly detection methods for precise anomaly localization and high-quality normal image reconstruction on the MVTec-AD benchmark.
What Makes for Good Tokenizers in Vision Transformer?
The architecture of transformers, which recently witness booming applications in vision tasks, has pivoted against the widespread convolutional paradigm.
General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignments
In this paper, we use Deep Generative Networks (DGNs) with a novel training mechanism to eliminate the distribution gap.
Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization
We propose a ray registration process based on the stylized reference view to obtain pseudo-ray supervision in novel views.
Image Inpainting via Iteratively Decoupled Probabilistic Modeling
To achieve high-quality results with low computational cost, we present a novel pixel spread model (PSM) that iteratively employs decoupled probabilistic modeling, combining the optimization efficiency of GANs with the prediction tractability of probabilistic models.
High-Quality Entity Segmentation
It improves mask prediction by fusing high-res image crops that provide more fine-grained image details and the full image.
Generalized Parametric Contrastive Learning
Based on theoretical analysis, we observe that supervised contrastive loss tends to bias high-frequency classes and thus increases the difficulty of imbalanced learning.
Ranked #5 on
Long-tail Learning
on iNaturalist 2018
End-to-end View Synthesis via NeRF Attention
On the one hand, NeRFA considers the volumetric rendering equation as a soft feature modulation procedure.
DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation
Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations.
Tracking Objects as Pixel-wise Distributions
During inference, a pixel-wise association procedure is proposed to recover object connections through frames based on the pixel-wise prediction.
Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution
Despite the quality improvement brought by the recent methods, video super-resolution (SR) is still very challenging, especially for videos that are low-light and noisy.
Towards Real-World Video Denosing: A Practical Video Denosing Dataset and Network
Moreover, we also propose a new video denoising framework, called Recurrent Video Denoising Transformer (RVDT), which can achieve SOTA performance on PVDD and other current video denoising benchmarks.
LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs
Recent advance in 2D CNNs has revealed that large kernels are important.
EfficientNeRF: Efficient Neural Radiance Fields
Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes.
Unifying Voxel-based Representation with Transformer for 3D Object Detection
To this end, the modality-specific space is first designed to represent different inputs in the voxel feature space.
Voxel Field Fusion for 3D Object Detection
In this work, we present a conceptually simple yet effective framework for cross-modality 3D object detection, named voxel field fusion.
Video Frame Interpolation with Transformer
Video frame interpolation (VFI), which aims to synthesize intermediate frames of a video, has made remarkable progress with development of deep convolutional networks over past years.
Ranked #5 on
Video Frame Interpolation
on MSU Video Frame Interpolation
(VMAF metric)
Focal Sparse Convolutional Networks for 3D Object Detection
In this paper, we introduce two new modules to enhance the capability of Sparse CNNs, both are based on making feature sparsity learnable with position-wise importance prediction.
DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors
First, to effectively lift the 2D information to stereo volume, we propose depth-wise plane sweeping (DPS) that allows denser connections and extracts depth-guided features.
Region Rebalance for Long-Tailed Semantic Segmentation
In this paper, we study the problem of class imbalance in semantic segmentation.
Ranked #21 on
Semantic Segmentation
on ADE20K
Multi-View Transformer for 3D Visual Grounding
The multi-view space enables the network to learn a more robust multi-modal representation for 3D visual grounding and eliminates the dependence on specific views.
MAT: Mask-Aware Transformer for Large Hole Image Inpainting
Recent studies have shown the importance of modeling long-range interactions in the inpainting problem.
Ranked #1 on
Image Inpainting
on CelebA-HQ
Stratified Transformer for 3D Point Cloud Segmentation
In this paper, we propose Stratified Transformer that is able to capture long-range contexts and demonstrates strong generalization ability and high performance.
Ranked #14 on
Semantic Segmentation
on ScanNet
Rebalanced Siamese Contrastive Mining for Long-Tailed Recognition
Given the promising performance of contrastive learning, we propose Rebalanced Siamese Contrastive Mining (ResCom) to tackle imbalanced recognition.
Ranked #5 on
Long-tail Learning
on CIFAR-10-LT (ρ=10)
SEA: Bridging the Gap Between One- and Two-stage Detector Distillation via SEmantic-aware Alignment
We revisit the one- and two-stage detector distillation tasks and present a simple and efficient semantic-aware framework to fill the gap between them.
A Unified Query-based Paradigm for Point Cloud Understanding
This is achieved by introducing an intermediate representation, i. e., Q-representation, in the querying stage to serve as a bridge between the embedding stage and task heads.
Ranked #7 on
Semantic Segmentation
on S3DIS
EfficientNeRF Efficient Neural Radiance Fields
Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes.
SNR-Aware Low-Light Image Enhancement
They are long-range operations for image regions of extremely low Signal-to-Noise-Ratio (SNR) and short-range operations for other regions.
Ranked #2 on
Low-Light Image Enhancement
on LIME
TWIST: Two-Way Inter-Label Self-Training for Semi-Supervised 3D Instance Segmentation
We explore the way to alleviate the label-hungry problem in a semi-supervised setting for 3D instance segmentation.
On Efficient Transformer-Based Image Pre-training for Low-Level Vision
Pre-training has marked numerous state of the arts in high-level computer vision, while few attempts have ever been made to investigate how pre-training acts in image processing systems.
Ranked #5 on
Image Super-Resolution
on Set5 - 2x upscaling
(using extra training data)
CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation
To improve instance-level detection/segmentation performance, existing self-supervised and semi-supervised methods extract either task-unrelated or task-specific training signals from unlabeled data.
High Quality Segmentation for Ultra High-resolution Images
To segment 4K or 6K ultra high-resolution images needs extra computation consideration in image segmentation.
Blending Anti-Aliasing into Vision Transformer
In this work, we analyze the uncharted problem of aliasing in vision transformer and explore to incorporate anti-aliasing properties.
Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation
To address the high cost and challenges of 3D point-level labeling, we present a method for semi-supervised point cloud semantic segmentation to adopt unlabeled point clouds in training to boost the model performance.
PFENet++: Boosting Few-shot Semantic Segmentation with the Noise-filtered Context-aware Prior Mask
In this work, we revisit the prior mask guidance proposed in ``Prior Guided Feature Enrichment Network for Few-Shot Segmentation''.
Deep Structured Instance Graph for Distilling Object Detectors
Effectively structuring deep knowledge plays a pivotal role in transfer from teacher to student, especially in semantic vision tasks.
Image Synthesis via Semantic Composition
In this paper, we present a novel approach to synthesize realistic images based on their semantic layouts.
Multi-Scale Aligned Distillation for Low-Resolution Detection
However, this option traditionally hurts the detection performance much.
Exploring and Improving Mobile Level Vision Transformers
We analyze the reason behind this phenomenon, and propose a novel irregular patch embedding module and adaptive patch fusion module to improve the performance.
Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision
In particular, Panoptic FCN encodes each object instance or stuff category with the proposed kernel generator and produces the prediction by convolving the high-resolution feature directly.
Conditional Temporal Variational AutoEncoder for Action Video Prediction
To synthesize a realistic action sequence based on a single human image, it is crucial to model both motion patterns and diversity in the action video.
Open-World Entity Segmentation
By removing the need of class label prediction, the models trained for such task can focus more on improving segmentation quality.
Parametric Contrastive Learning
In this paper, we propose Parametric Contrastive Learning (PaCo) to tackle long-tailed recognition.
Ranked #12 on
Long-tail Learning
on iNaturalist 2018
Semi-supervised Semantic Segmentation with Directional Context-aware Consistency
Semantic segmentation has made tremendous progress in recent years.
Self-Supervised 3D Mesh Reconstruction From Single Images
Recent single-view 3D reconstruction methods reconstruct object's shape and texture from a single image with only 2D image-level annotation.
MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution
Therefore, high-quality correspondence matching is critical.
LAPAR: Linearly-Assembled Pixel-Adaptive Regression Network for Single Image Super-Resolution and Beyond
Single image super-resolution (SISR) deals with a fundamental problem of upsampling a low-resolution (LR) image to its high-resolution (HR) version.
Distilling Knowledge via Knowledge Review
Knowledge distillation transfers knowledge from the teacher network to the student one, with the goal of greatly improving the performance of the student network.
Ranked #12 on
Knowledge Distillation
on CIFAR-100
Improving Calibration for Long-Tailed Recognition
Motivated by the fact that predicted probability distributions of classes are highly related to the numbers of class instances, we propose label-aware smoothing to deal with different degrees of over-confidence for classes and improve classifier learning.
Ranked #16 on
Long-tail Learning
on CIFAR-10-LT (ρ=100)
Jigsaw Clustering for Unsupervised Visual Representation Learning
It is even comparable to the contrastive learning methods when only half of training batches are used.
Scale-aware Automatic Augmentation for Object Detection
We propose Scale-aware AutoAug to learn data augmentation policies for object detection.
Best-Buddy GANs for Highly Detailed Image Super-Resolution
We consider the single image super-resolution (SISR) problem, where a high-resolution (HR) image is generated based on a low-resolution (LR) input.
Bidirectional Projection Network for Cross Dimension Scene Understanding
Via the \emph{BPM}, complementary 2D and 3D information can interact with each other in multiple architectural levels, such that advantages in these two visual domains can be combined for better scene recognition.
Ranked #11 on
Semantic Segmentation
on ScanNet
Video Instance Segmentation with a Propose-Reduce Paradigm
Video instance segmentation (VIS) aims to segment and associate all instances of predefined classes for each frame in videos.
Ranked #2 on
Unsupervised Video Object Segmentation
on DAVIS 2017 (val)
(using extra training data)
ResLT: Residual Learning for Long-tailed Recognition
From this perspective, the trivial solution utilizes different branches for the head, medium, and tail classes respectively, and then sums their outputs as the final results is not feasible.
Ranked #20 on
Long-tail Learning
on iNaturalist 2018
General Adversarial Defense via Pixel Level and Feature Level Distribution Alignment
Specifically, compared with previous methods, we propose a more efficient pixel-level training constraint to weaken the hardness of aligning adversarial samples to clean samples, which can thus obviously enhance the robustness on adversarial samples.
Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset With Mechatronic Alignment
Low-light video enhancement is an important task.
Point Transformer
For example, on the challenging S3DIS dataset for large-scale semantic scene segmentation, the Point Transformer attains an mIoU of 70. 4% on Area 5, outperforming the strongest prior model by 3. 3 absolute percentage points and crossing the 70% mIoU threshold for the first time.
Ranked #3 on
3D Semantic Segmentation
on STPLS3D
GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation
Note that GeoNet++ is generic and can be used in other depth/normal prediction frameworks to improve the quality of 3D reconstruction and pixel-wise accuracy of depth and surface normals.
Fully Convolutional Networks for Panoptic Segmentation
In this paper, we present a conceptually simple, strong, and efficient framework for panoptic segmentation, called Panoptic FCN.
Ranked #1 on
Panoptic Segmentation
on COCO minival
(SQ metric)
Learnable Boundary Guided Adversarial Training
Previous adversarial training raises model robustness under the compromise of accuracy on natural data.
Ranked #1 on
Adversarial Defense
on CIFAR-100
Generalized Few-shot Semantic Segmentation
Then, since context is essential for semantic segmentation, we propose the Context-Aware Prototype Learning (CAPL) that significantly improves performance by 1) leveraging the co-occurrence prior knowledge from support samples, and 2) dynamically enriching contextual information to the classifier, conditioned on the content of each query image.
Prior Guided Feature Enrichment Network for Few-Shot Segmentation
It consists of novel designs of (1) a training-free prior mask generation method that not only retains generalization power but also improves model performance and (2) Feature Enrichment Module (FEM) that overcomes spatial inconsistency by adaptively enriching query features with support features and prior masks.
Ranked #66 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
MuCAN: Multi-Correspondence Aggregation Network for Video Super-Resolution
Motivated by these findings, we propose a temporal multi-correspondence aggregation strategy to leverage similar patches across frames, and a cross-scale nonlocal-correspondence aggregation scheme to explore self-similarity of images across scales.
Exploring Self-attention for Image Recognition
Recent work has shown that self-attention can serve as a basic building block for image recognition models.
Dynamic Scale Training for Object Detection
We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection.
Attentive Normalization for Conditional Image Generation
Traditional convolution-based generative adversarial networks synthesize images based on hierarchical local operations, where long-range dependency relation is implicitly modeled with a Markov chain.
PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation
Instance segmentation is an important task for scene understanding.
Ranked #5 on
3D Instance Segmentation
on STPLS3D
VCNet: A Robust Approach to Blind Image Inpainting
Blind inpainting is a task to automatically complete visual contents without specifying masks for missing areas in an image.
Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation
Adversarial training is promising for improving robustness of deep neural networks towards adversarial perturbations, especially on the classification task.
PointINS: Point-based Instance Segmentation
In this paper, we explore the mask representation in instance segmentation with Point-of-Interest (PoI) features.
3DSSD: Point-based 3D Single Stage Object Detector
Our method outperforms all state-of-the-art voxel-based single stage methods by a large margin, and has comparable performance to two stage point-based methods as well, with inference speed more than 25 FPS, 2x faster than former state-of-the-art point-based methods.
GridMask Data Augmentation
Then we show limitation of existing information dropping algorithms and propose our structured method, which is simple and yet very effective.
DSGN: Deep Stereo Geometry Network for 3D Object Detection
Most state-of-the-art 3D object detectors heavily rely on LiDAR sensors because there is a large performance gap between image-based and LiDAR-based methods.
Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation
To incorporate point features in the edge branch, we establish a hierarchical graph framework, where the graph is initialized from a coarse layer and gradually enriched along the point decoding process.
Ranked #41 on
Semantic Segmentation
on S3DIS Area5
Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Translation
Facial landmark detection, or face alignment, is a fundamental task that has been extensively studied.
Ranked #18 on
Face Alignment
on WFLW
Fast Point R-CNN
We present a unified, efficient and effective framework for point-cloud based 3D object detection.
STD: Sparse-to-Dense 3D Object Detector for Point Cloud
We present a new two-stage 3D object detection framework, named sparse-to-dense 3D Object Detector (STD).
Attribute-Driven Spontaneous Motion in Unpaired Image Translation
Current image translation methods, albeit effective to produce high-quality results in various applications, still do not consider much geometric transform.
Landmark Assisted CycleGAN for Cartoon Face Generation
In this paper, we are interested in generating an cartoon face of a person by using unpaired training data between real faces and cartoon ones.
Region Refinement Network for Salient Object Detection
Albeit intensively studied, false prediction and unclear boundaries are still major issues of salient object detection.
Associatively Segmenting Instances and Semantics in Point Clouds
A 3D point cloud describes the real scene precisely and intuitively. To date how to segment diversified elements in such an informative 3D scene is rarely discussed.
Ranked #15 on
3D Instance Segmentation
on S3DIS
(mRec metric)
Human Pose Estimation with Spatial Contextual Information
With this principle, we present two conceptually simple and yet computational efficient modules, namely Cascade Prediction Fusion (CPF) and Pose Graph Neural Network (PGNN), to exploit underlying contextual information.
Ranked #10 on
Pose Estimation
on MPII Human Pose
IPOD: Intensive Point-based Object Detector for Point Cloud
We present a novel 3D object detection framework, named IPOD, based on raw point cloud.
Ranked #1 on
3D Object Detection
on KITTI Pedestrians Easy
Image Inpainting via Generative Multi-column Convolutional Neural Networks
In this paper, we propose a generative multi-column network for image inpainting.
Sequential Context Encoding for Duplicate Removal
Duplicate removal is a critical step to accomplish a reasonable amount of predictions in prevalent proposal-based object detection frameworks.
GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction
We propose to add geometric adversarial loss (GAL).
Compositing-aware Image Search
We present a new image search technique that, given a background image, returns compatible foreground objects for image compositing tasks.
PSANet: Point-wise Spatial Attention Network for Scene Parsing
We notice information flow in convolutional neural networks is restricted inside local neighborhood regions due to the physical design of convolutional filters, which limits the overall understanding of complex scenes.
Ranked #51 on
Semantic Segmentation
on Cityscapes test
SegStereo: Exploiting Semantic Information for Disparity Estimation
Disparity estimation for binocular stereo images finds a wide range of applications.
Ranked #6 on
Semantic Segmentation
on KITTI Semantic Segmentation
GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation
In this paper, we propose Geometric Neural Network (GeoNet) to jointly predict depth and surface normal maps from a single image.
Referring Image Segmentation via Recurrent Refinement Networks
We address the problem of image segmentation from natural language descriptions.
Semi-parametric Image Synthesis
We present a semi-parametric approach to photographic image synthesis from semantic layouts.
Facelet-Bank for Fast Portrait Manipulation
Digital face manipulation has become a popular and fascinating way to touch images with the prevalence of smartphones and social networks.
Path Aggregation Network for Instance Segmentation
The way that information propagates in neural networks is of great importance.
Ranked #3 on
Object Detection
on iSAID
Scale-recurrent Network for Deep Image Deblurring
In single image deblurring, the "coarse-to-fine" scheme, i. e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches.
Ranked #3 on
Image Deblurring
on GoPro
(Params (M) metric, using extra
training data)
Makeup-Go: Blind Reversion of Portrait Edit
In this paper, we propose the task of restoring a portrait image from this process.
3D Graph Neural Networks for RGBD Semantic Segmentation
Each node in the graph corresponds to a set of points and is associated with a hidden representation vector initialized with an appearance feature extracted by a unary CNN from 2D images.
Ranked #30 on
Semantic Segmentation
on SUN-RGBD
(using extra training data)
SGN: Sequential Grouping Networks for Instance Segmentation
By exploiting two-directional information, the second network groups horizontal and vertical lines into connected components.
Unsupervised Learning of Stereo Matching
However, due to the limitations of these datasets and the difficulty of collecting new stereo data, current methods fail in real-life cases.
Situation Recognition with Graph Neural Networks
We address the problem of recognizing situations in images.
Ranked #9 on
Situation Recognition
on imSitu
Automatic Real-time Background Cut for Portrait Videos
A spatial-temporal refinement network is developed to further refine the segmentation errors in each frame and ensure temporal coherence in the segmentation map.
ICNet for Real-Time Semantic Segmentation on High-Resolution Images
We focus on the challenging task of real-time semantic segmentation in this paper.
Ranked #10 on
Dichotomous Image Segmentation
on DIS-TE4
Dichotomous Image Segmentation
Real-Time Semantic Segmentation
+3
Zero-order Reverse Filtering
In this paper, we study an unconventional but practically meaningful reversibility problem of commonly used image filters.
Detail-revealing Deep Video Super-resolution
In this paper, we show that proper frame alignment and motion compensation is crucial for achieving high quality results.
Ranked #11 on
Video Super-Resolution
on Vid4 - 4x upscaling
High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits
Estimating correspondence between two images and extracting the foreground object are two challenges in computer vision.
Convolutional Neural Pyramid for Image Processing
We propose a principled convolutional neural pyramid (CNP) framework for general low-level vision and image processing tasks.
Pyramid Scene Parsing Network
Scene parsing is challenging for unrestricted open vocabulary and diverse scenes.
Ranked #4 on
Video Semantic Segmentation
on Cityscapes val
Visual Question Answering with Question Representation Update (QRU)
Our method aims at reasoning over natural language questions and visual images.
Multi-Scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation
Aiming at simultaneous detection and segmentation (SDS), we propose a proposal-free framework, which detect and segment object instances via mid-level patches.
ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
Large-scale data is of crucial importance for learning semantic segmentation models, but annotating per-pixel masks is a tedious and inefficient procedure.
A Closed-Form Solution to Tensor Voting: Theory and Applications
We prove a closed-form solution to tensor voting (CFTV): given a point set in any dimensions, our closed-form solution provides an exact, continuous and efficient algorithm for computing a structure-aware tensor that simultaneously achieves salient structure detection and outlier attenuation.
Contour Box: Rejecting Object Proposals Without Explicit Closed Contours
Closed contour is an important objectness indicator.
Box Aggregation for Proposal Decimation: Last Mile of Object Detection
Regions-with-convolutional-neural-network (RCNN) is now a commonly employed object detection pipeline.
Semantic Segmentation With Object Clique Potential
In this paper, we propose an object clique potential for semantic segmentation.
Mutual-Structure for Joint Filtering
Previous joint/guided filters directly transfer the structural information in the reference image to the target one.
Video Super-Resolution via Deep Draft-Ensemble Learning
We propose a new direction for fast video super-resolution (VideoSR) via a SR draft ensemble, which is defined as the set of high-resolution patch candidates before final image deconvolution.
ENFT: Efficient Non-Consecutive Feature Tracking for Robust Structure-from-Motion
Our framework consists of steps of solving the feature `dropout' problem when indistinctive structures, noise or large image distortion exists, and of rapidly recognizing and joining common features located in different subsequences.
Just Noticeable Defocus Blur Detection and Estimation
We tackle a fundamental problem to detect and estimate just noticeable blur (JNB) caused by defocus that spans a small number of pixels in images.
Deep LAC: Deep Localization, Alignment and Classification for Fine-Grained Recognition
Our major contribution is to propose a valve linkage function(VLF) for back-propagation chaining and form our deep localization, alignment and classification (LAC) system.
Handling Motion Blur in Multi-Frame Super-Resolution
Ubiquitous motion blur easily fails multi-frame super-resolution (MFSR).
Bounded-Distortion Metric Learning
Metric learning aims to embed one metric space into another to benefit tasks like classification and clustering.
Understanding and Diagnosing Visual Tracking Systems
Surprisingly, our findings are discrepant with some common beliefs in the visual tracking research community.
Deep Convolutional Neural Network for Image Deconvolution
Many fundamental image-related problems involve deconvolution operators.
Ranked #1 on
Image Compression
on FER2013
Hierarchical Saliency Detection on Extended CSSD
Complex structures commonly exist in natural images.
Discriminative Blur Detection Features
Ubiquitous image blur brings out a practically important question what are effective features to differentiate between blurred and unblurred image regions.
Learning Important Spatial Pooling Regions for Scene Classification
We address the false response influence problem when learning and applying discriminative parts to construct the mid-level representation in scene classification.
100+ Times Faster Weighted Median Filter (WMF)
Weighted median, in the form of either solver or filter, has been employed in a wide range of computer vision solutions for its beneficial properties in sparsity representation.
2D Semantic Segmentation task 1 (8 classes)
Optical Flow Estimation
+2
Two-Class Weather Classification
Given a single outdoor image, this paper proposes a collaborative learning approach for labeling it as either sunny or cloudy.
L0 Regularized Stationary Time Estimation for Crowd Group Analysis
We tackle stationary crowd analysis in this paper, which is similarly important as modeling mobile groups in crowd scenes and finds many applications in surveillance.
ESSP: An Efficient Approach to Minimizing Dense and Nonsubmodular Energy Functions
From our study, we make some reasonable recommendations of combining existing methods that perform the best in different situations for this challenging problem.
Dense Scattering Layer Removal
We propose a new model, together with advanced optimization, to separate a thick scattering media layer from a single natural image.
Online Robust Dictionary Learning
Online dictionary learning is particularly useful for processing large-scale and dynamic data in computer vision.
Unnatural L0 Sparse Representation for Natural Image Deblurring
We show in this paper that the success of previous maximum a posterior (MAP) based blur removal methods partly stems from their respective intermediate steps, which implicitly or explicitly create an unnatural representation containing salient image structures.
Ranked #13 on
Deblurring
on RealBlur-R (trained on GoPro)
(SSIM (sRGB) metric)
Hierarchical Saliency Detection
When dealing with objects with complex structures, saliency detection confronts a critical problem namely that detection accuracy could be adversely affected if salient foreground or background in an image contains small-scale high-contrast patterns.
