Search Results for author:
Found 88 papers, 53 papers with code
Pluggable Style Representation Learning for Multi-Style Transfer
Specifically, for style modeling, we propose a style representation learning scheme to encode the style information into a compact representation.
OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging
Online zero-shot 3D instance segmentation of a progressively reconstructed scene is both a critical and challenging task for embodied applications.
3D Instance Segmentation
open vocabulary 3d instance segmentation
+2
AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers
Post-training quantization (PTQ) has emerged as a promising solution for reducing the storage and computational cost of vision transformers (ViTs).
Layout2Scene: 3D Semantic Layout Guided Scene Generation via Geometry and Appearance Diffusion Priors
To fully leverage 2D diffusion priors in geometry and appearance generation, we introduce a semantic-guided geometry diffusion model and a semantic-geometry guided diffusion model which are finetuned on a scene dataset.
3D Registration in 30 Years: A Survey
3D point cloud registration is a fundamental problem in computer vision, computer graphics, robotics, remote sensing, and etc.
VideoDirector: Precise Video Editing via Text-to-Video Models
Despite the typical inversion-then-editing paradigm using text-to-image (T2I) models has demonstrated promising results, directly extending it to text-to-video (T2V) models still suffers severe artifacts such as color flickering and content distortion.
MaskBlur: Spatial and Angular Data Augmentation for Light Field Image Super-Resolution
Extensive experiments demonstrate the efficacy of MaskBlur in significantly enhancing the performance of existing SR methods.
NTIRE 2024 Challenge on Stereo Image Super-Resolution: Methods and Results
This paper summarizes the 3rd NTIRE challenge on stereo image super-resolution (SR) with a focus on new solutions and results.
DuInNet: Dual-Modality Feature Interaction for Point Cloud Completion
Besides the fully supervised point cloud completion task, two additional tasks including denoising completion and zero-shot learning completion are proposed in ModelNet-MPC, to simulate real-world scenarios and verify the robustness to noise and the transfer ability across categories of current methods.
Preserving Full Degradation Details for Blind Image Super-Resolution
In addition, we develop an energy distance loss to facilitate the learning of the degradation representations by introducing a bounded constraint.
DriveWorld: 4D Pre-trained Scene Understanding via World Models for Autonomous Driving
In this paper, we address this challenge by introducing a world model-based autonomous driving 4D representation learning framework, dubbed \emph{DriveWorld}, which is capable of pre-training from multi-camera driving videos in a spatio-temporal fashion.
Density-guided Translator Boosts Synthetic-to-Real Unsupervised Domain Adaptive Segmentation of 3D Point Clouds
3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to annotating new domains.
Learning Hierarchical Color Guidance for Depth Map Super-Resolution
On the one hand, the low-level detail embedding module is designed to supplement high-frequency color information of depth features in a residual mask manner at the low-level stages.
Sketch2NeRF: Multi-view Sketch-guided Text-to-3D Generation
We propose a novel synchronized generation and reconstruction method to effectively optimize the NeRF.
Sports-QA: A Large-Scale Video Question Answering Benchmark for Complex and Professional Sports
Reasoning over sports videos for question answering is an important task with numerous applications, such as player training and information retrieval.
Learning Coupled Dictionaries from Unpaired Data for Image Super-Resolution
The difficulty of acquiring high-resolution (HR) and low-resolution (LR) image pairs in real scenarios limits the performance of existing learning-based image super-resolution (SR) methods in the real world.
LoS: Local Structure-Guided Stereo Matching
In this paper we exploit local structure information (LSI) to enhance stereo matching.
L4D-Track: Language-to-4D Modeling Towards 6-DoF Tracking and Shape Reconstruction in 3D Point Cloud Stream
To this end we present a generic Language-to-4D modeling paradigm termed L4D-Track that tackles zero-shot 6-DoF \underline Track ing and shape reconstruction by learning pairwise implicit 3D representation and multi-level multi-modal alignment.
Point Contrastive Prediction with Semantic Clustering for Self-Supervised Learning on Point Cloud Videos
Instead of contrasting the representations of clips or frames, in this paper, we propose a unified self-supervised framework by conducting contrastive learning at the point level.
Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos
In this paper, we propose a Masked Spatio-Temporal Structure Prediction (MaST-Pre) method to capture the structure of point cloud videos without human annotations.
2D3D-MATR: 2D-3D Matching Transformer for Detection-free Registration between Images and Point Clouds
The commonly adopted detect-then-match approach to registration finds difficulties in the cross-modality cases due to the incompatible keypoint detection and inconsistent feature description.
GeoTransformer: Fast and Robust Point Cloud Registration with Geometric Transformer
They seek correspondences over downsampled superpoints, which are then propagated to dense points.
Variational Probabilistic Fusion Network for RGB-T Semantic Segmentation
RGB-T semantic segmentation has been widely adopted to handle hard scenes with poor lighting conditions by fusing different modality features of RGB and thermal images.
Ranked #19 on
Thermal Image Segmentation
on MFN Dataset
PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videos
Self-supervised learning can extract representations of good quality from solely unlabeled data, which is appealing for point cloud videos due to their high labelling cost.
NTIRE 2023 Challenge on Light Field Image Super-Resolution: Dataset, Methods and Results
In this report, we summarize the first NTIRE challenge on light field (LF) image super-resolution (SR), which aims at super-resolving LF images under the standard bicubic degradation with a magnification factor of 4.
Monte Carlo Linear Clustering with Single-Point Supervision is Enough for Infrared Small Target Detection
The core idea of this work is to recover the per-pixel mask of each target from the given single point label by using clustering approaches, which looks simple but is indeed challenging since targets are always insalient and accompanied with background clutters.
Robust Multiview Point Cloud Registration with Reliable Pose Graph Initialization and History Reweighting
Previous multiview registration methods rely on exhaustive pairwise registration to construct a densely-connected pose graph and apply Iteratively Reweighted Least Square (IRLS) on the pose graph to compute the scan poses.
Semi-Weakly Supervised Object Kinematic Motion Prediction
First, although 3D dataset with fully annotated motion labels is limited, there are existing datasets and methods for object part semantic segmentation at large scale.
Pseudo-label Correction and Learning For Semi-Supervised Object Detection
Our proposed method, Pseudo-label Correction and Learning (PCL), is extensively evaluated on the MS COCO and PASCAL VOC benchmarks.
Learning Non-Local Spatial-Angular Correlation for Light Field Image Super-Resolution
Exploiting spatial-angular correlation is crucial to light field (LF) image super-resolution (SR), but is highly challenging due to its non-local property caused by the disparities among LF images.
VAPCNet: Viewpoint-Aware 3D Point Cloud Completion
In this paper, we thus propose an unsupervised viewpoint representation learning scheme for 3D point cloud completion without explicit viewpoint estimation.
BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration
Extensive experiments on real-world scenarios demonstrate that our method achieves the best of both worlds in accuracy, efficiency, and generalization.
3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud
In-depth understanding of a 3D scene not only involves locating/recognizing individual objects, but also requires to infer the relationships and interactions among them.
Context-Aware Alignment and Mutual Masking for 3D-Language Pre-Training
The current approaches for 3D visual reasoning are task-specific, and lack pre-training methods to learn generic representations that can transfer across various tasks.
Bridging the Domain Gap in Satellite Pose Estimation: a Self-Training Approach based on Geometrical Constraints
Recently, unsupervised domain adaptation in satellite pose estimation has gained increasing attention, aiming at alleviating the annotation cost for training deep models.
MTU-Net: Multi-level TransUNet for Space-based Infrared Tiny Ship Detection
Due to the extremely large image coverage area (e. g., thousands square kilometers), candidate targets in these images are much smaller, dimer, more changeable than those targets observed by aerial-based and land-based imaging devices.
Real-World Light Field Image Super-Resolution via Degradation Modulation
In our method, a practical LF degradation model is developed to formulate the degradation process of real LF images.
Deep Learning for Visual Speech Analysis: A Survey
Visual speech, referring to the visual domain of speech, has attracted increasing attention due to its wide applications, such as public security, medical treatment, military defense, and film entertainment.
4DAC: Learning Attribute Compression for Dynamic Point Clouds
In addition, we also propose a deep conditional entropy model to estimate the probability distribution of the transformed coefficients, by incorporating temporal context from consecutive point clouds and the motion estimation/compensation modules.
NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results
In this paper, we summarize the 1st NTIRE challenge on stereo image super-resolution (restoration of rich details in a pair of low-resolution stereo images) with a focus on new solutions and results.
RayMVSNet: Learning Ray-based 1D Implicit Fields for Accurate Multi-View Stereo
In particular, we propose RayMVSNet which learns sequential prediction of a 1D implicit field along each camera ray with the zero-crossing point indicating scene depth.
Semantic-Aware Domain Generalized Segmentation
In this paper, we address domain generalized semantic segmentation, where a segmentation model is trained to be domain-invariant without using any target domain data.
Not All Points Are Equal: Learning Highly Efficient Point-based Detectors for 3D LiDAR Point Clouds
To reduce the memory and computational cost, existing point-based pipelines usually adopt task-agnostic random sampling or farthest point sampling to progressively downsample input point clouds, despite the fact that not all points are equally important to the task of object detection.
Depth Estimation by Combining Binocular Stereo and Monocular Structured-Light
In order to verify the effectiveness of the proposed system, we build a prototype and collect a test dataset in indoor scenes.
3DAC: Learning Attribute Compression for Point Clouds
Finally, the estimated probabilities are used to further compress these transform coefficients to a final attributes bitstream.
Occlusion-Aware Cost Constructor for Light Field Depth Estimation
Based on the proposed cost constructor, we develop a deep network for LF depth estimation.
Disentangling Light Fields for Super-Resolution and Disparity Estimation
In this paper, we propose a generic mechanism to disentangle these coupled information for LF image processing.
Geometric Transformer for Fast and Robust Point Cloud Registration
Such sparse and loose matching requires contextual features capturing the geometric structure of the point clouds.
Box2Seg: Learning Semantics of 3D Point Clouds with Box-Level Supervision
In this paper, we introduce a neural architecture, termed Box2Seg, to learn point-level semantics of 3D point clouds with bounding box-level supervision.
Decoupling Makes Weakly Supervised Local Feature Better
Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences.
Ranked #1 on
Camera Localization
on Aachen Day-Night benchmark
Learnable Lookup Table for Neural Network Quantization
Since a linear quantizer (i. e., round(*) function) cannot well fit the bell-shaped distributions of weights and activations, many existing methods use pre-defined functions (e. g., exponential function) with learnable parameters to build the quantizer for joint optimization.
Detecting and Tracking Small and Dense Moving Objects in Satellite Videos: A Benchmark
Satellite video cameras can provide continuous observation for a large-scale area, which is important for many remote sensing applications.
Spatial-Temporal Transformer for 3D Point Cloud Sequences
We test the effectiveness our PST2 with two different tasks on point cloud sequences, i. e., 4D semantic segmentation and 3D action recognition.
Selective Light Field Refocusing for Camera Arrays Using Bokeh Rendering and Superresolution
In this letter, we propose a light field refocusing method to improve the imaging quality of camera arrays.
Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation
Domain adaptation is critical for success when confronting with the lack of annotations in a new domain.
Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling
We study the problem of efficient semantic segmentation of large-scale 3D point clouds.
Bilateral Grid Learning for Stereo Matching Networks
In this paper, we present a novel edge-preserving cost volume upsampling module based on the slicing operation in the learned bilateral grid.
Dense Nested Attention Network for Infrared Small Target Detection
With the repeated interaction in DNIM, infrared small targets in deep layers can be maintained.
SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds
Labelling point clouds fully is highly time-consuming and costly.
Unsupervised Degradation Representation Learning for Blind Super-Resolution
In this paper, we propose an unsupervised degradation representation learning scheme for blind SR without explicit degradation estimation.
Deep Learning for Scene Classification: A Survey
Scene classification, aiming at classifying a scene image to one of the predefined scene categories by comprehending the entire image, is a longstanding, fundamental and challenging problem in computer vision.
SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration
Extracting robust and general 3D local features is key to downstream tasks such as point cloud registration and reconstruction.
Ranked #2 on
Point Cloud Registration
on ETH (trained on 3DMatch)
Symmetric Parallax Attention for Stereo Image Super-Resolution
Although recent years have witnessed the great advances in stereo image super-resolution (SR), the beneficial information provided by binocular systems has not been fully used.
Distortion-aware Monocular Depth Estimation for Omnidirectional Images
A main challenge for tasks on panorama lies in the distortion of objects among images.
A Practical Tutorial on Graph Neural Networks
Graph neural networks (GNNs) have recently grown in popularity in the field of artificial intelligence (AI) due to their unique ability to ingest relatively unstructured data types as input data.
Parallax Attention for Unsupervised Stereo Correspondence Learning
Based on our PAM, we propose a parallax-attention stereo matching network (PASMnet) and a parallax-attention stereo image super-resolution network (PASSRnet) for stereo matching and stereo image super-resolution tasks.
Axiom-based Grad-CAM: Towards Accurate Visualization and Explanation of CNNs
To have a better understanding and usage of Convolution Neural Networks (CNNs), the visualization and interpretation of CNNs has attracted increasing attention in recent years.
Light Field Image Super-Resolution Using Deformable Convolution
In this paper, we propose a deformable convolution network (i. e., LF-DFnet) to handle the disparity problem for LF image SR.
Pseudo-LiDAR Point Cloud Interpolation Based on 3D Motion Representation and Spatial Supervision
Pseudo-LiDAR point cloud interpolation is a novel and challenging task in the field of autonomous driving, which aims to address the frequency mismatching problem between camera and LiDAR.
Exploring Sparsity in Image Super-Resolution for Efficient Inference
Specifically, we develop a Sparse Mask SR (SMSR) network to learn sparse masks to prune redundant computation.
Learning Local Features with Context Aggregation for Visual Localization
Most existing methods use detect-then-describe or detect-and-describe strategy to learn local features without considering their context information.
Learning A Single Network for Scale-Arbitrary Super-Resolution
In this paper, we propose to learn a scale-arbitrary image SR network from scale-specific networks.
Deformable 3D Convolution for Video Super-Resolution
In this paper, we propose a deformable 3D convolution network (D3Dnet) to incorporate spatio-temporal information from both spatial and temporal dimensions for video SR.
Deep Video Super-Resolution using HR Optical Flow Estimation
The key challenge for video SR lies in the effective exploitation of temporal dependency between consecutive frames.
Ranked #6 on
Video Super-Resolution
on MSU Super-Resolution for Video Compression
(BSQ-rate over ERQA metric)
Deep Learning for 3D Point Clouds: A Survey
To stimulate future research, this paper presents a comprehensive review of recent progress in deep learning methods for point clouds.
Spatial-Angular Interaction for Light Field Image Super-Resolution
Specifically, spatial and angular features are first separately extracted from input LFs, and then repetitively interacted to progressively incorporate spatial and angular information.
DeOccNet: Learning to See Through Foreground Occlusions in Light Fields
In this paper, we handle the LF de-occlusion (LF-DeOcc) problem using a deep encoder-decoder network (namely, DeOccNet).
RandLA-Net: Efficient Semantic Segmentation of Large-Scale Point Clouds
We study the problem of efficient semantic segmentation for large-scale 3D point clouds.
Ranked #2 on
3D Semantic Segmentation
on Toronto-3D
PLIN: A Network for Pseudo-LiDAR Point Cloud Interpolation
In this paper, we propose a novel Pseudo-LiDAR interpolation network (PLIN) to increase the frequency of LiDAR sensors.
Unsupervised Primitive Discovery for Improved 3D Generative Modeling
Using the primitive parts for shapes as attributes, a parameterized 3D representation is modeled in the first stage.
Flickr1024: A Large-Scale Dataset for Stereo Image Super-Resolution
With the popularity of dual cameras in recently released smart phones, a growing number of super-resolution (SR) methods have been proposed to enhance the resolution of stereo image pairs.
Learning Parallax Attention for Stereo Image Super-Resolution
Stereo image pairs can be used to improve the performance of super-resolution (SR) since additional information is provided from a second viewpoint.
Ranked #1 on
Image Super-Resolution
on KITTI 2012 - 4x upscaling
A Sketch Based 3D Shape Retrieval Approach Based on Efficient Deep Point-to-Subspace Metric Learning
A sketch based 3D shape retrieval
Learning for Video Super-Resolution through HR Optical Flow Estimation
Extensive experiments demonstrate that HR optical flows provide more accurate correspondences than their LR counterparts and improve both accuracy and consistency performance.
Ranked #18 on
Video Super-Resolution
on Vid4 - 4x upscaling
Learning for Disparity Estimation through Feature Constancy
The second part performs matching cost calculation, matching cost aggregation and disparity calculation to estimate the initial disparity using shared features.
Partial Procedural Geometric Model Fitting for Point Clouds
However, most geometric model fitting methods are unable to fit an arbitrary geometric model (e. g. a surface with holes) to incomplete data, due to that the similarity metrics used in these methods are unable to measure the rigid partial similarity between arbitrary models.
Rotational Projection Statistics for 3D Local Surface Description and Object Recognition
The performance of the proposed LRF, RoPS descriptor and object recognition algorithm was rigorously tested on a number of popular and publicly available datasets.
