BAL: Balancing Diversity and Novelty for Active Learning

PFENet++: Boosting Few-Shot Semantic Segmentation with the Noise-Filtered Context-Aware Prior Mask

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

SaCo Loss: Sample-wise Affinity Consistency for Vision-Language Pre-training

Scalable Language Model with Generalized Continual Learning

Adaptive Perspective Distillation for Semantic Segmentation

Conditional Temporal Variational AutoEncoder for Action Video Prediction

DSGN++: Exploiting Visual-Spatial Relation for Stereo-Based 3D Detectors

Fully Convolutional Networks for Panoptic Segmentation with Point-Based Supervision

Open World Entity Segmentation

ResLT: Residual Learning for Long-Tailed Recognition

Scale-Aware Automatic Augmentations for Object Detection With Dynamic Training

What Makes for Good Tokenizers in Vision Transformer?

Command-driven Articulated Object Understanding and Manipulation

Deep Parametric 3D Filters for Joint Video Denoising and Illumination Enhancement in Video Super Resolution

DiffComplete: Diffusion-based Generative 3D Shape Completion

End-to-end 3D Tracking with Decoupled Queries

FocalFormer3D : Focusing on Hard Instance for 3D Object Detection

Hierarchical Dense Correlation Distillation for Few-Shot Segmentation

High Quality Entity Segmentation

LargeKernel3D: Scaling up Kernels in 3D Sparse CNNs

Learning Context-Aware Classifier for Semantic Segmentation

Mask-Attention-Free Transformer for 3D Instance Segmentation

Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields

Real-World Image Variation by Aligning Diffusion Inversion Chain

Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization

Removing Anomalies as Noises for Industrial Defect Localization

Rethinking Out-of-distribution (OOD) Detection: Masked Image Modeling is All You Need

Spherical Transformer for LiDAR-Based 3D Recognition

TriVol: Point Cloud Rendering via Triple Volumes

Understanding Imbalanced Semantic Segmentation Through Neural Collapse

VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking

GeoNet++: Iterative Geometric Neural Network with Edge-Aware Refinement for Joint Depth and Surface Normal Estimation

Homomorphic Interpolation Network for Unpaired Image-to-Image Translation

PointINS: Point-Based Instance Segmentation

Prior Guided Feature Enrichment Network for Few-Shot Segmentation

Text-Guided Human Image Manipulation via Image-Text Shared Space

A Unified Query-based Paradigm for Point Cloud Understanding

CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation

DecoupleNet: Decoupled Network for Domain Adaptive Semantic Segmentation

EfficientNeRF - Efficient Neural Radiance Fields

Focal Sparse Convolutional Networks for 3D Object Detection

Generalized Few-shot Semantic Segmentation

High Quality Segmentation for Ultra High-resolution Images

MAT: Mask-Aware Transformer for Large Hole Image Inpainting

Multi-View Transformer for 3D Visual Grounding

SNR-Aware Low-light Image Enhancement

Stratified Transformer for 3D Point Cloud Segmentation

Tracking Objects as Pixel-Wise Distributions

TWIST: Two-Way Inter-label Self-Training for Semi-supervised 3D Instance Segmentation

Unifying Voxel-based Representation with Transformer for 3D Object Detection

Video Frame Interpolation with Transformer

Voxel Field Fusion for 3D Object Detection

Bidirectional projection network for cross dimension scene understanding

Blending Anti-Aliasing into Vision Transformer

Deep Structured Instance Graph for Distilling Object Detectors

Distilling Knowledge via Knowledge Review

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation

Fully Convolutional Networks for Panoptic Segmentation

Guided Point Contrastive Learning for Semi-supervised Point Cloud Semantic Segmentation

Image Synthesis via Semantic Composition

Improving calibration for long-tailed recognition

Jigsaw Clustering for Unsupervised Visual Representation Learning

Learnable Boundary Guided Adversarial Training

MASA-SR: Matching Acceleration and Spatial Adaptation for Reference-Based Image Super-Resolution

Multi-scale aligned distillation for low-resolution detection

Parametric Contrastive Learning

Point Transformer

Scale-aware Automatic Augmentation for Object Detection

Seeing Dynamic Scene in the Dark: A High-Quality Video Dataset with Mechatronic Alignment

Self-Supervised 3D Mesh Reconstruction from Single Images

Semi-supervised Semantic Segmentation with Directional Context-aware Consistency

Video Instance Segmentation with a Propose-Reduce Paradigm

3DSSD: Point-based 3d single stage object detector

Aggregation via separation: Boosting facial landmark detector with semi-supervised style translation

Amodal instance segmentation with kins dataset

Attentive normalization for conditional image generation

CN: Channel Normalization for Point Cloud Recognition

Domain adaptive image-to-image translation

DSGN: Deep Stereo Geometry Network for 3D Object Detection

Exploring Self-attention for Image Recognition

Fast and practical neural architecture search

Fast point R-CNN

Hierarchical point-edge interaction network for point cloud semantic segmentation

LAPAR: Linearly-assembled pixel-adaptive regression network for single image super-resolution and beyond

Memory Selection Network for Video Propagation

MuCAN: Multi-correspondence Aggregation Network for Video Super-Resolution

Particularity Beyond Commonality: Unpaired Identity Transfer with Multiple References

PointGroup: Dual-set point grouping for 3D instance segmentation

STD: Sparse-to-dense 3D object detector for point cloud

VCNet: A Robust Approach to Blind Image Inpainting

Fast Abnormal Event Detection

3D Motion Decomposition for RGBD Future Dynamic Scene Synthesis

AGSS-VOS: Attention guided single-shot video object segmentation

Associatively segmenting instances and semantics in point clouds

Attribute-driven spontaneous motion in unpaired image translation

Dynamic scene deblurring with parameter selective sharing and nested skip connections

Homomorphic latent space interpolation for unpaired image-to-image translation

Learning shape-aware embedding for scene text detection

Pointweb: Enhancing local neighborhood features for point cloud processing

Semantic component decomposition for face attribute manipulation

Underexposed photo enhancement using deep illumination estimation

View independent generative adversarial network for novel view synthesis

Wide-context semantic image extrapolation

Compositing-Aware Image Search

Facelet-Bank for Fast Portrait Manipulation

GAL: Geometric adversarial loss for single-view 3D-object reconstruction

GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation

ICNet for Real-Time Semantic Segmentation on High-Resolution Images

Image inpainting via generative multi-column convolutional neural networks

Path Aggregation Network for Instance Segmentation

PSANet: Point-wise spatial attention network for scene parsing

Referring Image Segmentation via Recurrent Refinement Networks

Scale-Recurrent Network for Deep Image Deblurring

SegStereo: Exploiting semantic information for disparity estimation

Semi-Parametric Image Synthesis

Sequential context encoding for duplicate removal

L₀ Regularized Stationary-Time Estimation for Crowd Analysis

Mutual-Structure for Joint Filtering

RSCM: Region Selection and Concurrency Model for Multi-Class Weather Recognition

Two-Class Weather Classification

3D Graph Neural Networks for RGBD Semantic Segmentation

Detail-Revealing Deep Video Super-Resolution

High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits

Makeup-Go: Blind Reversion of Portrait Edit

Pyramid scene parsing network

SGN: Sequential Grouping Networks for Instance Segmentation

Situation Recognition with Graph Neural Networks

Unsupervised Learning of Stereo Matching

Zero-Order Reverse Filtering

Efficient Non-Consecutive Feature Tracking for Robust Structure-From-Motion

Hierarchical Image Saliency Detection on Extended CSSD

Multi-Viewpoint Panorama Construction with Wide-Baseline Images

Regional foremost matching for internet scene images

Augmented feedback in semantic segmentation under image level supervision

Multi-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

Visual question answering with question representation update (QRU)

Break Ames room illusion: Depth from general single images

Multispectral Joint Image Restoration via Optimizing a Scale Map

Personal object discovery in first-person videos

Box aggregation for proposal decimation: Last mile of object detection

Contour Box: Rejecting Object Proposals without Explicit Closed Contours

Deep edge-aware filters

Deep LAC: Deep Localization, Alignment and Classification for Fine-Grained Recognition

Handling motion blur in multi-frame super-resolution

High-quality depth recovery via interactive multi-view stereo

Just noticeable defocus blur detection and estimation

Mutual-structure for joint filtering

Photometric Stereo in the Wild

Semantic segmentation with object clique potential

Understanding and Diagnosing Visual Tracking Systems

Video super-resolution via deep draft-ensemble learning

Contrast Preserving Decolorization with Perception-Based Quality Metrics

Efficient keyframe-based real-time camera tracking

Scale adaptive dictionary learning

100+ times faster weighted median filter (WMF)

Deep convolutional neural network for image deconvolution

Discriminative blur detection features

Inverse kernels for fast spatial deconvolution

L₀ regularized stationary time estimation for crowd group analysis

Learning Important Spatial Pooling Regions for Scene Classification

Multi-modal and multi-spectral registration for natural images

Range-sample depth feature for action recognition

Rolling guidance filter

Two-class weather classification

A sparse control model for image and video editing

Consistent binocular depth and scene flow with chained temporal profiles

Mathematical models and practical solvers for uniform motion deblurring

Abnormal event detection at 150 FPS in MATLAB

CoDeL: A human co-detection and labeling framework

Cross-field joint image restoration via scale map

Dense scattering layer removal

Forward motion deblurring

Hierarchical saliency detection

Online robust dictionary learning

SCMF: Sparse Covariance Matrix Factorization for Collaborative Filtering

Unnatural L₀ sparse representation for natural image deblurring

A closed-form solution to tensor voting: Theory and applications

ImageAdmixture: Putting together dissimilar objects from groups

Improving sub-pixel correspondence through upsampling

Motion detail preserving optical flow estimation

Structure extraction from texture via relative total variation

Combining sketch and tone for pencil drawing production

Contrast preserving decolorization

Depth-aware motion deblurring

Discriminative Clustering via Generative Feature Mapping

Learning sparse covariance patterns for natural scenes

Real-time contrast preserving decolorization

Real-time contrast preserving decolorization

Scale invariant optical flow

Image Smoothing via L₀ Gradient Minimization

Motion imitation with a handheld camera

Robust bilayer segmentation and motion/depth estimation with a handheld camera

Image smoothing via L₀ gradient minimization

Simultaneous multi-body stereo and segmentation

A unified framework for designing textures using energy optimization

Globally optimized linear windowed tone mapping

Modeling and Rendering of Impossible Figures

Self-validated labeling of Markov random fields for image segmentation

Efficient non-consecutive feature tracking for structure-from-motion

Motion detail preserving optical flow estimation

Quasi-dense 3D Reconstruction Using Tensor-based Multiview Stereo

Two-phase kernel estimation for robust motion deblurring

Using optical defocus to denoise

Consistent depth maps recovery from a video sequence

Fractional stereo matching using expectation-maximization

Refilming with depth-inferred videos

Keyframe-Based Real-Time Camera Tracking

Minimizing sparse higher order energy functions of discrete variables

Fast Image/Video Upsampling

High-quality motion deblurring from a single image

Image stitching using structure deformation

A segmentation based variational model for accurate optical flow estimation

Efficient photometric stereo on glossy surfaces with wide specular lobes

Fast image/video upsampling

Image partial blur detection and classification

Recovering consistent video depth maps via bundle optimization

Reducing boundary artifacts in image deconvolution

Stereo matching: An outlier confidence approach

Soft color segmentation and its applications

Active Window Oriented Dynamic Video Retargeting

Moving object extraction with a hand-held camera

Rotational motion deblurring of a rigid object from a single image

Single image motion deblurring using transparency

Stereo matching on objects with fractional boundary

Drag-and-drop pasting

Video repairing under variable illumination using cyclic motions

Drag-and-drop pasting

Image completion with structure propagation

Tensor voting for image correction by global and local intensity alignment

Eliminating structure and intensity misalignment in image stitching

Local color transfer via probabilistic segmentation by expectation-maximization

Inference of segmented color and texture description by tensor voting

Poisson Matting

Bayesian correction of image intensity with spatial consideration

Poisson matting

Video repairing: Inference of foreground and background under severe occlusion

Image registration with global and local luminance alignment

Image repairing: Robust image synthesis by adaptive ND tensor voting

Compositing-Aware Image Search

Conference paper

Facelet-Bank for Fast Portrait Manipulation

Conference paper

GAL: Geometric adversarial loss for single-view 3D-object reconstruction

Conference paper

GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation

Conference paper

ICNet for Real-Time Semantic Segmentation on High-Resolution Images

Conference paper

Image inpainting via generative multi-column convolutional neural networks

Conference paper

Path Aggregation Network for Instance Segmentation

Conference paper

PSANet: Point-wise spatial attention network for scene parsing

Conference paper

Referring Image Segmentation via Recurrent Refinement Networks

Conference paper

Scale-Recurrent Network for Deep Image Deblurring

Conference paper

SegStereo: Exploiting semantic information for disparity estimation

Conference paper

Semi-Parametric Image Synthesis

Conference paper

Sequential context encoding for duplicate removal

Conference paper

L₀ Regularized Stationary-Time Estimation for Crowd Analysis

Article

Mutual-Structure for Joint Filtering

Article

RSCM: Region Selection and Concurrency Model for Multi-Class Weather Recognition

Article

Two-Class Weather Classification

Article

3D Graph Neural Networks for RGBD Semantic Segmentation

Conference paper

Detail-Revealing Deep Video Super-Resolution

Conference paper

High-Quality Correspondence and Segmentation Estimation for Dual-Lens Smart-Phone Portraits

Conference paper

Makeup-Go: Blind Reversion of Portrait Edit

Conference paper

Pyramid scene parsing network

Conference paper

SGN: Sequential Grouping Networks for Instance Segmentation

Conference paper

Situation Recognition with Graph Neural Networks

Conference paper

Unsupervised Learning of Stereo Matching

Conference paper

Zero-Order Reverse Filtering

Conference paper

Efficient Non-Consecutive Feature Tracking for Robust Structure-From-Motion

Article

Hierarchical Image Saliency Detection on Extended CSSD

Article

Multi-Viewpoint Panorama Construction with Wide-Baseline Images

Article

Regional foremost matching for internet scene images

Article

Augmented feedback in semantic segmentation under image level supervision

Conference paper

Multi-scale Patch Aggregation (MPA) for Simultaneous Detection and Segmentation

Conference paper

ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation

Conference paper

Visual question answering with question representation update (QRU)

Conference paper

Break Ames room illusion: Depth from general single images

Article

Multispectral Joint Image Restoration via Optimizing a Scale Map

Article

Personal object discovery in first-person videos

Article

Box aggregation for proposal decimation: Last mile of object detection

Conference paper

Contour Box: Rejecting Object Proposals without Explicit Closed Contours

Conference paper

Deep edge-aware filters

Conference paper

Deep LAC: Deep Localization, Alignment and Classification for Fine-Grained Recognition

Conference paper

Handling motion blur in multi-frame super-resolution

Conference paper

High-quality depth recovery via interactive multi-view stereo

Conference paper

Just noticeable defocus blur detection and estimation

Conference paper

Mutual-structure for joint filtering

Conference paper

Photometric Stereo in the Wild

Conference paper

Semantic segmentation with object clique potential

Conference paper

Understanding and Diagnosing Visual Tracking Systems

Conference paper

Video super-resolution via deep draft-ensemble learning

Conference paper

Contrast Preserving Decolorization with Perception-Based Quality Metrics

Article

Efficient keyframe-based real-time camera tracking

Article

Scale adaptive dictionary learning

Article

100+ times faster weighted median filter (WMF)

Conference paper

Deep convolutional neural network for image deconvolution

Conference paper

Discriminative blur detection features

Conference paper

Inverse kernels for fast spatial deconvolution

Conference paper

L₀ regularized stationary time estimation for crowd group analysis

Conference paper

Learning Important Spatial Pooling Regions for Scene Classification

Conference paper

Multi-modal and multi-spectral registration for natural images

Conference paper

Range-sample depth feature for action recognition

Conference paper

Rolling guidance filter

Conference paper

Two-class weather classification

Conference paper

A sparse control model for image and video editing

Article

Consistent binocular depth and scene flow with chained temporal profiles

Article

Mathematical models and practical solvers for uniform motion deblurring

Book chapter

Abnormal event detection at 150 FPS in MATLAB

Conference paper

CoDeL: A human co-detection and labeling framework

Conference paper

Cross-field joint image restoration via scale map

Conference paper

Dense scattering layer removal

Conference paper

Forward motion deblurring

Conference paper

Hierarchical saliency detection

Conference paper

Online robust dictionary learning

Conference paper

SCMF: Sparse Covariance Matrix Factorization for Collaborative Filtering

Conference paper

Unnatural L₀ sparse representation for natural image deblurring

Conference paper

A closed-form solution to tensor voting: Theory and applications

Article

ImageAdmixture: Putting together dissimilar objects from groups

Article

Improving sub-pixel correspondence through upsampling

Article

Motion detail preserving optical flow estimation

Article

Structure extraction from texture via relative total variation

Article

Combining sketch and tone for pencil drawing production

Conference paper

Contrast preserving decolorization

Conference paper

Depth-aware motion deblurring

Conference paper

Discriminative Clustering via Generative Feature Mapping

Conference paper

Learning sparse covariance patterns for natural scenes

Conference paper

Real-time contrast preserving decolorization

Conference paper

Real-time contrast preserving decolorization

Conference paper

Scale invariant optical flow

Conference paper

Image Smoothing via L₀ Gradient Minimization

Article

Motion imitation with a handheld camera

Article

Robust bilayer segmentation and motion/depth estimation with a handheld camera

Article

Image smoothing via L₀ gradient minimization

Conference paper

Simultaneous multi-body stereo and segmentation

Conference paper

A unified framework for designing textures using energy optimization

Article

Globally optimized linear windowed tone mapping

Article

Modeling and Rendering of Impossible Figures

Article

Self-validated labeling of Markov random fields for image segmentation

Article

Efficient non-consecutive feature tracking for structure-from-motion

Conference paper

Motion detail preserving optical flow estimation

Conference paper

Quasi-dense 3D Reconstruction Using Tensor-based Multiview Stereo

Conference paper

Two-phase kernel estimation for robust motion deblurring

Conference paper

Using optical defocus to denoise

Conference paper

Consistent depth maps recovery from a video sequence

Article

Fractional stereo matching using expectation-maximization

Article

Refilming with depth-inferred videos

Article

Keyframe-Based Real-Time Camera Tracking

Conference paper

Minimizing sparse higher order energy functions of discrete variables

Conference paper

Fast Image/Video Upsampling

Article

High-quality motion deblurring from a single image

Article

Image stitching using structure deformation

Article

A segmentation based variational model for accurate optical flow estimation

Conference paper

Efficient photometric stereo on glossy surfaces with wide specular lobes

Conference paper

Fast image/video upsampling

Conference paper

Image partial blur detection and classification

Conference paper

Recovering consistent video depth maps via bundle optimization

Conference paper

Reducing boundary artifacts in image deconvolution

Conference paper

Stereo matching: An outlier confidence approach

Conference paper

Soft color segmentation and its applications

Article

Active Window Oriented Dynamic Video Retargeting

Conference paper

Moving object extraction with a hand-held camera

Conference paper

Rotational motion deblurring of a rigid object from a single image

Conference paper

Single image motion deblurring using transparency

Conference paper

Stereo matching on objects with fractional boundary

Conference paper

Drag-and-drop pasting

Article

Video repairing under variable illumination using cyclic motions

Article

Drag-and-drop pasting

Conference paper

Image completion with structure propagation

Article

Tensor voting for image correction by global and local intensity alignment

Article

Eliminating structure and intensity misalignment in image stitching

Conference paper

Local color transfer via probabilistic segmentation by expectation-maximization

Conference paper

Inference of segmented color and texture description by tensor voting

Article

Poisson Matting

Article

Bayesian correction of image intensity with spatial consideration

Conference paper

Poisson matting

Conference paper

Video repairing: Inference of foreground and background under severe occlusion

Conference paper

Image registration with global and local luminance alignment

Conference paper

Image repairing: Robust image synthesis by adaptive ND tensor voting

Conference paper