Zhiguo Cao

19

Papers

202

Total Citations

Papers (19)

The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World

Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting

Unifying Automatic and Interactive Matting with Pretrained ViTs

3D Multi-frame Fusion for Video Stabilization

Semi-supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix

Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields

In-Context Matting

Training Matting Models Without Alpha Labels

DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting

Exploring Contextual Attribute Density in Referring Expression Counting

S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes

WildAvatar: Learning In-the-wild 3D Avatars from the Web

Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations

DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video

Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency

TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion

MuGS: Multi-Baseline Generalizable Gaussian Splatting Reconstruction

SRefiner: Soft-Braid Attention for Multi-Agent Trajectory Refinement

CH3Depth: Efficient and Flexible Depth Foundation Model with Flow Matching