Shengping Zhang

15

Papers

464

Total Citations

Papers (15)

ODTrack: Online Dense Temporal Token Learning for Visual Tracking

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

Autoregressive Queries for Adaptive Tracking with Spatio-Temporal Transformers

SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field

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

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

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

Revisiting Context Aggregation for Image Matting

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

ProsodyTalker: 3D Visual Speech Animation via Prosody Decomposition

Mind the Boundary: Coreset Selection via Reconstructing the Decision Boundary

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

Multi-view Consistent 3D Panoptic Scene Understanding

Explicit Visual Prompts for Visual Object Tracking