Shengping Zhang

papers

2,332

total citations

papers (21)

Siamese Box Adaptive Network for Visual Tracking

CVPR 2020arXiv

807

citations

GRNet: Gridding Residual Network for Dense Point Cloud Completion

ECCV 2020arXiv

402

citations

GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians

CVPR 2024arXiv

197

citations

ODTrack: Online Dense Temporal Token Learning for Visual Tracking

AAAI 2024arXiv

188

citations

GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis

CVPR 2024arXiv

166

citations

ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning

CVPR 2024arXiv

citations

Revisiting Context Aggregation for Image Matting

ICML 2024arXiv

citations

Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints

AAAI 2025arXiv

citations

Multi-view Consistent 3D Panoptic Scene Understanding

AAAI 2025

citations

Mind the Boundary: Coreset Selection via Reconstructing the Decision Boundary

ICML 2024

citations

Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring

ICML 2024

citations

ProsodyTalker: 3D Visual Speech Animation via Prosody Decomposition

AAAI 2025

citations

DiffPerformer: Iterative Learning of Consistent Latent Guidance for Diffusion-based Human Video Generation

CVPR 2024

citations

Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring

CVPR 2024

citations

Shengping Zhang

papers (21)

Siamese Box Adaptive Network for Visual Tracking

GRNet: Gridding Residual Network for Dense Point Cloud Completion

GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians

ODTrack: Online Dense Temporal Token Learning for Visual Tracking

GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis

Efficient Regional Memory Network for Video Object Segmentation

Object-and-Action Aware Model for Visual Language Navigation

Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers

Explicit Visual Prompts for Visual Object Tracking

Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy

CaPhy: Capturing Physical Properties for Animatable Human Avatars

SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field

ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning

Revisiting Context Aggregation for Image Matting

Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints

Multi-view Consistent 3D Panoptic Scene Understanding

Mind the Boundary: Coreset Selection via Reconstructing the Decision Boundary

Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring

ProsodyTalker: 3D Visual Speech Animation via Prosody Decomposition

DiffPerformer: Iterative Learning of Consistent Latent Guidance for Diffusion-based Human Video Generation

Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring

papers (21)

Siamese Box Adaptive Network for Visual Tracking

GRNet: Gridding Residual Network for Dense Point Cloud Completion

GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians

ODTrack: Online Dense Temporal Token Learning for Visual Tracking

GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis

Efficient Regional Memory Network for Video Object Segmentation

Object-and-Action Aware Model for Visual Language Navigation

Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers

Explicit Visual Prompts for Visual Object Tracking

Distractor-Aware Fast Tracking via Dynamic Convolutions and MOT Philosophy

CaPhy: Capturing Physical Properties for Animatable Human Avatars

SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field

ProxyCap: Real-time Monocular Full-body Capture in World Space via Human-Centric Proxy-to-Motion Learning

Revisiting Context Aggregation for Image Matting

Path-Adaptive Matting for Efficient Inference Under Various Computational Cost Constraints

Multi-view Consistent 3D Panoptic Scene Understanding

Mind the Boundary: Coreset Selection via Reconstructing the Decision Boundary

Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring

ProsodyTalker: 3D Visual Speech Animation via Prosody Decomposition

DiffPerformer: Iterative Learning of Consistent Latent Guidance for Diffusion-based Human Video Generation

Fourier Priors-Guided Diffusion for Zero-Shot Joint Low-Light Enhancement and Deblurring