Zhiguo Cao

63 papers · 2017–2026 · 6 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (7) 🐝 Cross-Pollinator (5) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🗺️ Taxonomy Completionist (86) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (6) 🏃 Academic Marathon (8) 🏠 Conference Loyalist (24) 🤝 Dynamic Duo (23) 👥 Mega-Team (35) 🔬 Deep Specialist (11) 🏆 Keyword Champion (2) 💎 Century Club (58) ⚡ Prolific Year (15) 🔥 Unstoppable (9) 🗃️ Keyword Collector (244)

Conferences

CVPR (24) ICCV (13) ECCV (12) AAAI (11) NIPS (2) ICLR (1)

Top co-authors

Hao Lu (23) Ke Xian (13) Tianqi Liu (12) Yang Xiao (11) Zihao Huang (10) Huiqiang Sun (10) Liao Shen (9) Xinyi Ye (9) Zhiyu Pan (9) Jiaqi Li (8)

Research topics

Computer Vision (1)

Keywords

depth estimation (11) object detection (8) 3d reconstruction (5) temporal consistency (5) novel view synthesis (5) semantic segmentation (4) feature matching (4) point cloud (4) image matting (4) autonomous driving (3) attention mechanism (3) neural radiance field (3) multi-view stereo (3) image cropping (3) image generation (2) video understanding (2) temporal modeling (2) trajectory prediction (2) hand pose estimation (2) data augmentation (2)

Papers

DEFANet: Dual-Path Edge-Target Collaboration with Frequency-Aware Enhancement for Infrared Small Target Detection AAAI 2026

BokehCrafter: Taming Video Diffusion Models for Controllable Bokeh Rendering AAAI 2026

Semi-Supervised High Dynamic Range Image Reconstructing via Bi-Level Uncertain Area Masking AAAI 2026

BokehFlow: Depth-Free Controllable Bokeh Rendering via Flow Matching AAAI 2026

DeFB: Decomposed Feature Learning for Real-Time Multi-Person Eyeblink Detection in Untrimmed In-the-Wild Videos AAAI 2026

SRefiner: Soft-Braid Attention for Multi-Agent Trajectory Refinement ICCV 2025

MuGS: Multi-Baseline Generalizable Gaussian Splatting Reconstruction ICCV 2025

Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency ICCV 2025

DoF-Gaussian: Controllable Depth-of-Field for 3D Gaussian Splatting CVPR 2025

CH3Depth: Efficient and Flexible Depth Foundation Model with Flow Matching CVPR 2025

Exploring Contextual Attribute Density in Referring Expression Counting CVPR 2025

WildAvatar: Learning In-the-wild 3D Avatars from the Web CVPR 2025

TacoDepth: Towards Efficient Radar-Camera Depth Estimation with One-stage Fusion CVPR 2025

Training Matting Models Without Alpha Labels AAAI 2025

Geometry-aware Reconstruction and Fusion-refined Rendering for Generalizable Neural Radiance Fields CVPR 2024

Self-Distilled Depth Refinement with Noisy Poisson Fusion NIPS 2024

Semi-supervised Class-Agnostic Motion Prediction with Pseudo Label Regeneration and BEVMix AAAI 2024

Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting AAAI 2024

Self-Supervised Class-Agnostic Motion Prediction with Spatial and Temporal Consistency Regularizations CVPR 2024

In-Context Matting CVPR 2024

S-DyRF: Reference-Based Stylized Radiance Fields for Dynamic Scenes CVPR 2024

DyBluRF: Dynamic Neural Radiance Fields from Blurry Monocular Video CVPR 2024

3D Multi-frame Fusion for Video Stabilization CVPR 2024

Unifying Automatic and Interactive Matting with Pretrained ViTs CVPR 2024

Dynamic Neural Radiance Field From Defocused Monocular Video ECCV 2024

DreamMover: Leveraging the Prior of Diffusion Models for Image Interpolation with Large Motion ECCV 2024

MVSGaussian: Fast Generalizable Gaussian Splatting Reconstruction from Multi-View Stereo ECCV 2024

CrossGLG: LLM Guides One-shot Skeleton-based 3D Action Recognition in a Cross-level Manner ECCV 2024

The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World ICLR 2024

Infusing Definiteness into Randomness: Rethinking Composition Styles for Deep Image Matting AAAI 2023

Learning Second-Order Attentive Context for Efficient Correspondence Pruning AAAI 2023

Real-Time Multi-Person Eyeblink Detection in the Wild for Untrimmed Video CVPR 2023

Fast Full-frame Video Stabilization with Iterative Optimization ICCV 2023

Learning to Upsample by Learning to Sample ICCV 2023

Point-Query Quadtree for Crowd Counting, Localization, and More ICCV 2023

Neural Video Depth Stabilizer ICCV 2023

Matching Is Not Enough: A Two-Stage Framework for Category-Agnostic Pose Estimation CVPR 2023

Find Beauty in the Rare: Contrastive Composition Feature Clustering for Nontrivial Cropping Box Regression AAAI 2023

Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells ICCV 2023

3D Cinemagraphy From a Single Image CVPR 2023

When Epipolar Constraint Meets Non-Local Operators in Multi-View Stereo ICCV 2023

A2J-Transformer: Anchor-to-Joint Transformer Network for 3D Interacting Hand Pose Estimation From a Single RGB Image CVPR 2023

BokehMe: When Neural Rendering Meets Classical Rendering CVPR 2022

Represent, Compare, and Learn: A Similarity-Aware Framework for Class-Agnostic Counting CVPR 2022

C3P: Cross-Domain Pose Prior Propagation for Weakly Supervised 3D Human Pose Estimation ECCV 2022

MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects ECCV 2022

Robust Object Detection with Inaccurate Bounding Boxes ECCV 2022

FADE: Fusing the Assets of Decoder and Encoder for Task-Agnostic Upsampling ECCV 2022

3D Instances as 1D Kernels ECCV 2022

SAPA: Similarity-Aware Point Affiliation for Feature Upsampling NIPS 2022

Composing Photos Like a Photographer CVPR 2021

TransView: Inside, Outside, and Across the Cropping View Boundaries ICCV 2021

P2B: Point-to-Box Network for 3D Object Tracking in Point Clouds CVPR 2020

Measuring Generalisation to Unseen Viewpoints, Articulations, Shapes and Objects for 3D Hand Pose Estimation under Hand-Object Interaction ECCV 2020

3DV: 3D Dynamic Voxel for Action Recognition in Depth Video CVPR 2020

Structure-Guided Ranking Loss for Single Image Depth Prediction CVPR 2020

Sparse-to-Dense Depth Completion Revisited: Sampling Strategy and Graph Construction ECCV 2020

Weighing Counts: Sequential Crowd Counting by Reinforcement Learning ECCV 2020

NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences CVPR 2019

From Open Set to Closed Set: Counting Objects by Spatial Divide-and-Conquer ICCV 2019

A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation From a Single Depth Image ICCV 2019

Monocular Relative Depth Perception With Web Stereo Data Supervision CVPR 2018

When Unsupervised Domain Adaptation Meets Tensor Representations ICCV 2017