Search Results for author:
Found 113 papers, 70 papers with code
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.
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.
How Good Are Low-bit Quantized LLaMA3 Models? An Empirical Study
This exploration holds the potential to unveil new insights and challenges for low-bit quantization of LLaMA3 and other forthcoming LLMs, especially in addressing performance degradation problems that suffer in LLM compression.
Groma: Localized Visual Tokenization for Grounding Multimodal Large Language Models
We introduce Groma, a Multimodal Large Language Model (MLLM) with grounded and fine-grained visual perception ability.
Efficient and accurate neural field reconstruction using resistive memory
The GE harnesses the intrinsic stochasticity of resistive memory for efficient input encoding, while the PE achieves precise weight mapping through a Hardware-Aware Quantization (HAQ) circuit.
Resistive Memory-based Neural Differential Equation Solver for Score-based Diffusion Model
Demonstrating equivalent generative quality to the software baseline, our system achieved remarkable enhancements in generative speed for both unconditional and conditional generation tasks, by factors of 64. 8 and 156. 5, respectively.
3DGSR: Implicit Surface Reconstruction with 3D Gaussian Splatting
In this paper, we present an implicit surface reconstruction method with 3D Gaussian Splatting (3DGS), namely 3DGSR, that allows for accurate 3D reconstruction with intricate details while inheriting the high efficiency and rendering quality of 3DGS.
Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction
Scene reconstruction from multi-view images is a fundamental problem in computer vision and graphics.
Can 3D Vision-Language Models Truly Understand Natural Language?
To test the language understandability of 3D-VL models, we first propose a language robustness task for systematically assessing 3D-VL models across various tasks, benchmarking their performance when presented with different language style variants.
DO3D: Self-supervised Learning of Decomposed Object-aware 3D Motion and Depth from Monocular Videos
Our system contains a depth estimation module to predict depth, and a new decomposed object-wise 3D motion (DO3D) estimation module to predict ego-motion and 3D object motion.
Classes Are Not Equal: An Empirical Study on Image Recognition Fairness
Second, with the proposed concept of Model Prediction Bias, we investigate the origins of problematic representation during optimization.
Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting
The recent advancements in 3D Gaussian splatting (3D-GS) have not only facilitated real-time rendering through modern GPU rasterization pipelines but have also attained state-of-the-art rendering quality.
Debiasing Text-to-Image Diffusion Models
Despite its simplicity, we show that IDA shows efficiency and fast convergence in resolving the social bias in TTI diffusion models.
EscherNet: A Generative Model for Scalable View Synthesis
We introduce EscherNet, a multi-view conditioned diffusion model for view synthesis.
BiLLM: Pushing the Limit of Post-Training Quantization for LLMs
Pretrained large language models (LLMs) exhibit exceptional general language processing capabilities but come with significant demands on memory and computational resources.
V-IRL: Grounding Virtual Intelligence in Real Life
There is a sensory gulf between the Earth that humans inhabit and the digital realms in which modern AI agents are created.
GO-NeRF: Generating Virtual Objects in Neural Radiance Fields
To this end, we propose a new method, GO-NeRF, capable of utilizing scene context for high-quality and harmonious 3D object generation within an existing NeRF.
UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation
Recent advancements in text-to-3D generation technology have significantly advanced the conversion of textual descriptions into imaginative well-geometrical and finely textured 3D objects.
Random resistive memory-based deep extreme point learning machine for unified visual processing
Our random resistive memory-based deep extreme point learning machine may pave the way for energy-efficient and training-friendly edge AI across various data modalities and tasks.
SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes
During learning, the location and number of control points are adaptively adjusted to accommodate varying motion complexities in different regions, and an ARAP loss following the principle of as rigid as possible is developed to enforce spatial continuity and local rigidity of learned motions.
Pruning random resistive memory for optimizing analogue AI
Here, we report a universal solution, software-hardware co-design using structural plasticity-inspired edge pruning to optimize the topology of a randomly weighted analogue resistive memory neural network.
EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation
This paper presents a new text-guided technique for generating 3D shapes.
Text-to-3D with Classifier Score Distillation
In this paper, we re-evaluate the role of classifier-free guidance in score distillation and discover a surprising finding: the guidance alone is enough for effective text-to-3D generation tasks.
CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection
CoDet then leverages visual similarities to discover the co-occurring objects and align them with the shared concept.
Ranked #2 on
Open Vocabulary Object Detection
on LVIS v1.0
(using extra training data)
SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features
In comparison to conventional RGB cameras, the superior temporal resolution of event cameras allows them to capture rich information between frames, making them prime candidates for object tracking.
Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video
Therefore, directly learning a mapping function from speech to the entire head image is prone to ambiguity, particularly when using a short video for training.
Texture Generation on 3D Meshes with Point-UV Diffusion
In this work, we focus on synthesizing high-quality textures on 3D meshes.
Lowis3D: Language-Driven Open-World Instance-Level 3D Scene Understanding
To address this challenge, we propose to harness pre-trained vision-language (VL) foundation models that encode extensive knowledge from image-text pairs to generate captions for multi-view images of 3D scenes.
Ranked #3 on
3D Open-Vocabulary Instance Segmentation
on S3DIS
3D Open-Vocabulary Instance Segmentation
Instance Segmentation
+4
MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds
Unlike the single-scan-based semantic segmentation task, this task requires distinguishing the motion states of points in addition to their semantic categories.
Decoupled Kullback-Leibler Divergence Loss
In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and observe that it is equivalent to the Doupled Kullback-Leibler (DKL) Divergence loss that consists of 1) a weighted Mean Square Error (wMSE) loss and 2) a Cross-Entropy loss incorporating soft labels.
Hybrid Neural Rendering for Large-Scale Scenes with Motion Blur
Rendering novel view images is highly desirable for many applications.
RegionPLC: Regional Point-Language Contrastive Learning for Open-World 3D Scene Understanding
Existing 3D scene understanding tasks have achieved high performance on close-set benchmarks but fail to handle novel categories in real-world applications.
Context-Aware Transformer for 3D Point Cloud Automatic Annotation
3D automatic annotation has received increased attention since manually annotating 3D point clouds is laborious.
You Only Need One Thing One Click: Self-Training for Weakly Supervised 3D Scene Understanding
3D scene understanding, e. g., point cloud semantic and instance segmentation, often requires large-scale annotated training data, but clearly, point-wise labels are too tedious to prepare.
DreamStone: Image as Stepping Stone for Text-Guided 3D Shape Generation
The core of our approach is a two-stage feature-space alignment strategy that leverages a pre-trained single-view reconstruction (SVR) model to map CLIP features to shapes: to begin with, map the CLIP image feature to the detail-rich 3D shape space of the SVR model, then map the CLIP text feature to the 3D shape space through encouraging the CLIP-consistency between rendered images and the input text.
IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation
Category-level 6D pose estimation aims to predict the poses and sizes of unseen objects from a specific category.
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
Learning a Room with the Occ-SDF Hybrid: Signed Distance Function Mingled with Occupancy Aids Scene Representation
We found that the color rendering loss results in optimization bias against low-intensity areas, causing gradient vanishing and leaving these areas unoptimized.
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.
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.
Vertical Layering of Quantized Neural Networks for Heterogeneous Inference
Experiments show that the proposed vertical-layered representation and developed once QAT scheme are effective in embodying multiple quantized networks into a single one and allow one-time training, and it delivers comparable performance as that of quantized models tailored to any specific bit-width.
PLA: Language-Driven Open-Vocabulary 3D Scene Understanding
Open-vocabulary scene understanding aims to localize and recognize unseen categories beyond the annotated label space.
Ranked #2 on
3D Open-Vocabulary Instance Segmentation
on S3DIS
3D Open-Vocabulary Instance Segmentation
Contrastive Learning
+4
MGFN: Magnitude-Contrastive Glance-and-Focus Network for Weakly-Supervised Video Anomaly Detection
Weakly supervised detection of anomalies in surveillance videos is a challenging task.
Anomaly Detection In Surveillance Videos
Video Anomaly Detection
Parametric Classification for Generalized Category Discovery: A Baseline Study
Generalized Category Discovery (GCD) aims to discover novel categories in unlabelled datasets using knowledge learned from labelled samples.
Ranked #1 on
Open-World Semi-Supervised Learning
on ImageNet-100
SL3D: Self-supervised-Self-labeled 3D Recognition
SL3D is a generic framework and can be applied to solve different 3D recognition tasks, including classification, object detection, and semantic segmentation.
Ranked #2 on
Unsupervised 3D Semantic Segmentation
on ScanNetV2
Is synthetic data from generative models ready for image recognition?
Recent text-to-image generation models have shown promising results in generating high-fidelity photo-realistic images.
Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection
Most existing 3D point cloud object detection approaches heavily rely on large amounts of labeled training data.
In-situ Model Downloading to Realize Versatile Edge AI in 6G Mobile Networks
We further propose a virtualized 6G network architecture customized for deploying in-situ model downloading with the key feature of a three-tier (edge, local, and central) AI library.
Spatial Pruned Sparse Convolution for Efficient 3D Object Detection
3D scenes are dominated by a large number of background points, which is redundant for the detection task that mainly needs to focus on foreground objects.
Rethinking Resolution in the Context of Efficient Video Recognition
Our key finding is that the major cause of degradation is not information loss in the down-sampling process, but rather the mismatch between network architecture and input scale.
ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation
Text-guided 3D shape generation remains challenging due to the absence of large paired text-shape data, the substantial semantic gap between these two modalities, and the structural complexity of 3D shapes.
Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing
With the rapid development of mobile devices, modern widely-used mobile phones typically allow users to capture 4K resolution (i. e., ultra-high-definition) images.
Ranked #1 on
Image Restoration
on UHDM
Multimodal Transformer for Automatic 3D Annotation and Object Detection
By enriching the sparse point clouds, our method achieves 4. 48\% and 4. 03\% better 3D AP on KITTI moderate and hard samples, respectively, versus the state-of-the-art autolabeler.
LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs
Recent advance in 2D CNNs has revealed that large kernels are important.
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.
Towards Efficient 3D Object Detection with Knowledge Distillation
Then, we build a benchmark to assess existing KD methods developed in the 2D domain for 3D object detection upon six well-constructed teacher-student pairs.
Self-Supervised Visual Representation Learning with Semantic Grouping
The semantic grouping is performed by assigning pixels to a set of learnable prototypes, which can adapt to each sample by attentive pooling over the feature and form new slots.
Ranked #15 on
Unsupervised Semantic Segmentation
on COCO-Stuff-27
(Accuracy metric)
Video Demoireing with Relation-Based Temporal Consistency
Moire patterns, appearing as color distortions, severely degrade image and video qualities when filming a screen with digital cameras.
DODA: Data-oriented Sim-to-Real Domain Adaptation for 3D Semantic Segmentation
Deep learning approaches achieve prominent success in 3D semantic segmentation.
MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator
While a few previous studies tried to automatically generate 3D bounding boxes from weak labels such as 2D boxes, the quality is sub-optimal compared to human annotators.
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
Towards Implicit Text-Guided 3D Shape Generation
In this work, we explore the challenging task of generating 3D shapes from text.
HINT: Hierarchical Neuron Concept Explainer
To this end, we propose HIerarchical Neuron concepT explainer (HINT) to effectively build bidirectional associations between neurons and hierarchical concepts in a low-cost and scalable manner.
Progressive End-to-End Object Detection in Crowded Scenes
Experiments show that our method can significantly boost the performance of query-based detectors in crowded scenes.
Ranked #1 on
Object Detection
on CrowdHuman
Knowledge Distillation as Efficient Pre-training: Faster Convergence, Higher Data-efficiency, and Better Transferability
Large-scale pre-training has been proven to be crucial for various computer vision tasks.
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.
Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
In this paper, we propose a simple yet effective recursive least-squares estimator-aided online learning approach for few-shot online adaptation without requiring offline training.
Slot-VPS: Object-centric Representation Learning for Video Panoptic Segmentation
We encode all panoptic entities in a video, including both foreground instances and background semantics, with a unified representation called panoptic slots.
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.
ST3D++: Denoised Self-training for Unsupervised Domain Adaptation on 3D Object Detection
These specific designs enable the detector to be trained on meticulously refined pseudo labeled target data with denoised training signals, and thus effectively facilitate adapting an object detector to a target domain without requiring annotations.
Multilevel Knowledge Transfer for Cross-Domain Object Detection
The key ingredients to our approach are -- (a) mapping the source to the target domain on pixel-level; (b) training a teacher network on the mapped source and the unannotated target domain using adversarial feature alignment; and (c) finally training a student network using the pseudo-labels obtained from the teacher.
Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation
In this paper, we present a simple and yet effective Distribution Alignment and Random Sampling (DARS) method to produce unbiased pseudo labels that match the true class distribution estimated from the labeled data.
3D-to-2D Distillation for Indoor Scene Parsing
First, we distill 3D knowledge from a pretrained 3D network to supervise a 2D network to learn simulated 3D features from 2D features during the training, so the 2D network can infer without requiring 3D data.
One Thing One Click: A Self-Training Approach for Weakly Supervised 3D Semantic Segmentation
Point cloud semantic segmentation often requires largescale annotated training data, but clearly, point-wise labels are too tedious to prepare.
PAConv: Position Adaptive Convolution with Dynamic Kernel Assembling on Point Clouds
The key of PAConv is to construct the convolution kernel by dynamically assembling basic weight matrices stored in Weight Bank, where the coefficients of these weight matrices are self-adaptively learned from point positions through ScoreNet.
Ranked #2 on
Point Cloud Segmentation
on PointCloud-C
AET-EFN: A Versatile Design for Static and Dynamic Event-Based Vision
The neuromorphic event cameras, which capture the optical changes of a scene, have drawn increasing attention due to their high speed and low power consumption.
ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
Then, the detector is iteratively improved on the target domain by alternatively conducting two steps, which are the pseudo label updating with the developed quality-aware triplet memory bank and the model training with curriculum data augmentation.
Aggregation With Feature Detection
Aggregating features from different depths of a network is widely adopted to improve the network capability.
Learning Geometry-Disentangled Representation for Complementary Understanding of 3D Object Point Cloud
GDANet introduces Geometry-Disentangle Module to dynamically disentangle point clouds into the contour and flat part of 3D objects, respectively denoted by sharp and gentle variation components.
Ranked #1 on
Point Cloud Segmentation
on PointCloud-C
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)
Object-aware Feature Aggregation for Video Object Detection
As a consequence, augmenting features with such prior knowledge can effectively improve the classification and localization performance.
Lightweight Generative Adversarial Networks for Text-Guided Image Manipulation
To achieve this, a new word-level discriminator is proposed, which provides the generator with fine-grained training feedback at word-level, to facilitate training a lightweight generator that has a small number of parameters, but can still correctly focus on specific visual attributes of an image, and then edit them without affecting other contents that are not described in the text.
Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis
We propose a novel ECGAN for the challenging semantic image synthesis task.
Image-to-Image Translation with Text Guidance
The goal of this paper is to embed controllable factors, i. e., natural language descriptions, into image-to-image translation with generative adversarial networks, which allows text descriptions to determine the visual attributes of synthetic images.
Global Texture Enhancement for Fake Face Detection in the Wild
In this paper, we conduct an empirical study on fake/real faces, and have two important observations: firstly, the texture of fake faces is substantially different from real ones; secondly, global texture statistics are more robust to image editing and transferable to fake faces from different GANs and datasets.
Gated Path Selection Network for Semantic Segmentation
Semantic segmentation is a challenging task that needs to handle large scale variations, deformations and different viewpoints.
Unifying Training and Inference for Panoptic Segmentation
This panoptic submodule gives rise to a novel propagation mechanism for panoptic logits and enables the network to output a coherent panoptic segmentation map for both "stuff" and "thing" classes, without any post-processing.
Few-shot Action Recognition with Permutation-invariant Attention
Such encoded blocks are aggregated by permutation-invariant pooling to make our approach robust to varying action lengths and long-range temporal dependencies whose patterns are unlikely to repeat even in clips of the same class.
Ranked #6 on
Few Shot Action Recognition
on Kinetics-100
An Adversarial Perturbation Oriented Domain Adaptation Approach for Semantic Segmentation
In contrast to adversarial alignment, we propose to explicitly train a domain-invariant classifier by generating and defensing against pointwise feature space adversarial perturbations.
ManiGAN: Text-Guided Image Manipulation
The goal of our paper is to semantically edit parts of an image matching a given text that describes desired attributes (e. g., texture, colour, and background), while preserving other contents that are irrelevant to the text.
Domain-invariant Stereo Matching Networks
State-of-the-art stereo matching networks have difficulties in generalizing to new unseen environments due to significant domain differences, such as color, illumination, contrast, and texture.
Controllable Text-to-Image Generation
In this paper, we propose a novel controllable text-to-image generative adversarial network (ControlGAN), which can effectively synthesise high-quality images and also control parts of the image generation according to natural language descriptions.
Ranked #7 on
Text-to-Image Generation
on Multi-Modal-CelebA-HQ
Improved Techniques for Training Adaptive Deep Networks
Adaptive inference is a promising technique to improve the computational efficiency of deep models at test time.
3D Motion Decomposition for RGBD Future Dynamic Scene Synthesis
A future video is the 2D projection of a 3D scene with predicted camera and object motion.
The Liver Tumor Segmentation Benchmark (LiTS)
In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018.
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
Image Inpainting via Generative Multi-column Convolutional Neural Networks
In this paper, we propose a generative multi-column network for image inpainting.
GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction
We propose to add geometric adversarial loss (GAL).
Referring Image Segmentation via Recurrent Refinement Networks
We address the problem of image segmentation from natural language descriptions.
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.
Semi-parametric Image Synthesis
We present a semi-parametric approach to photographic image synthesis from semantic layouts.
Semantically Consistent Image Completion with Fine-grained Details
Image completion has achieved significant progress due to advances in generative adversarial networks (GANs).
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)
H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes
Our method outperformed other state-of-the-arts on the segmentation results of tumors and achieved very competitive performance for liver segmentation even with a single model.
Ranked #1 on
Liver Segmentation
on LiTS2017
(Dice metric)
Automatic Liver And Tumor Segmentation
Image Segmentation
+4
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 #11 on
Dichotomous Image Segmentation
on DIS-TE4
Dichotomous Image Segmentation
Real-Time Semantic Segmentation
+3
Pyramid Scene Parsing Network
Scene parsing is challenging for unrestricted open vocabulary and diverse scenes.
Ranked #4 on
Video Semantic Segmentation
on Cityscapes val
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.
DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation
The morphology of glands has been used routinely by pathologists to assess the malignancy degree of adenocarcinomas.
Ranked #3 on
Optic Disc Segmentation
on REFUGE
Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest
Colorectal adenocarcinoma originating in intestinal glandular structures is the most common form of colon cancer.
Semantic Segmentation With Object Clique Potential
In this paper, we propose an object clique potential for semantic segmentation.
