Zhigang Wang

papers

968

total citations

papers (24)

One-Shot High-Fidelity Talking-Head Synthesis With Deformable Neural Radiance Field

CVPR 2023arXiv

citations

Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models

AAAI 2024arXiv

citations

SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation

ICML 2024arXiv

citations

Fully Self-Supervised Depth Estimation From Defocus Clue

CVPR 2023arXiv

citations

Any2Point: Empowering Any-modality Transformers for Efficient 3D Understanding

ECCV 2024

citations

MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation

ICCV 2025arXiv

citations

UFO: Unified Feature Optimization

ECCV 2022arXiv

citations

Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding

AAAI 2025arXiv

citations

X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-Modal Knowledge Transfer

AAAI 2024arXiv

citations

HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation

CVPR 2024arXiv

citations

Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction

ICCV 2023arXiv

citations

Efficient Diffusion as Low Light Enhancer

CVPR 2025arXiv

citations

Color Event Enhanced Single-Exposure HDR Imaging

AAAI 2024

citations

AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations

ICCV 2025arXiv

citations

Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation

CVPR 2025arXiv

citations

Open-Vocabulary Octree-Graph for 3D Scene Understanding

ICCV 2025arXiv

citations

Propagate and Calibrate: Real-Time Passive Non-Line-of-Sight Tracking

CVPR 2023arXiv

citations

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

AAAI 2025arXiv

citations

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

AAAI 2025arXiv

citations

Optimizing Human Pose Estimation Through Focused Human and Joint Regions

AAAI 2025arXiv

citations

Zhigang Wang

papers (24)

GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting

Implicit Sample Extension for Unsupervised Person Re-Identification

Unsupervised Multi-Source Domain Adaptation for Person Re-Identification

ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding

One-Shot High-Fidelity Talking-Head Synthesis With Deformable Neural Radiance Field

Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models

SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation

Fully Self-Supervised Depth Estimation From Defocus Clue

Any2Point: Empowering Any-modality Transformers for Efficient 3D Understanding

MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation

UFO: Unified Feature Optimization

Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding

X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-Modal Knowledge Transfer

HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation

Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction

Efficient Diffusion as Low Light Enhancer

Color Event Enhanced Single-Exposure HDR Imaging

AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations

Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation

Open-Vocabulary Octree-Graph for 3D Scene Understanding

Propagate and Calibrate: Real-Time Passive Non-Line-of-Sight Tracking

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

Optimizing Human Pose Estimation Through Focused Human and Joint Regions

papers (24)

GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting

Implicit Sample Extension for Unsupervised Person Re-Identification

Unsupervised Multi-Source Domain Adaptation for Person Re-Identification

ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding

One-Shot High-Fidelity Talking-Head Synthesis With Deformable Neural Radiance Field

Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models

SAM-E: Leveraging Visual Foundation Model with Sequence Imitation for Embodied Manipulation

Fully Self-Supervised Depth Estimation From Defocus Clue

Any2Point: Empowering Any-modality Transformers for Efficient 3D Understanding

MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation

UFO: Unified Feature Optimization

Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding

X4D-SceneFormer: Enhanced Scene Understanding on 4D Point Cloud Videos through Cross-Modal Knowledge Transfer

HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation

Towards Nonlinear-Motion-Aware and Occlusion-Robust Rolling Shutter Correction

Efficient Diffusion as Low Light Enhancer

Color Event Enhanced Single-Exposure HDR Imaging

AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations

Think Small, Act Big: Primitive Prompt Learning for Lifelong Robot Manipulation

Open-Vocabulary Octree-Graph for 3D Scene Understanding

Propagate and Calibrate: Real-Time Passive Non-Line-of-Sight Tracking

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

SpatioTemporal Learning for Human Pose Estimation in Sparsely-Labeled Videos

Optimizing Human Pose Estimation Through Focused Human and Joint Regions