Zihui Zhang

7 papers · 2021–2026 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (15)

Venues

CVPR (4) AAAI (1) ICLR (1) ICML (1)

Top co-authors

Bo Yang (6) Yafei YANG (4) Hongtao Wen (2) Shenxing Wei (2) Bing Wang (2) Jinxi Li (2) Chuhang Zou (1) Jiayue Huang (1) Dongsheng Wang (1) Bo Li (1)

Research topics

Computer Vision (7) Analysis (7) Deep Learning (5) Machine Learning (5) Learning Types · Machine Learning (4) Models (3) Learning Types · Deep Learning (2) Artificial Intelligence (1) Bayesian & Probabilistic (1) Core Methods (1) Generation (1) Learning Paradigms (1) Processing (1)

Keywords

point cloud (4) unsupervised learning (4) 3d vision (2) semantic segmentation (2) object-centric representation (2) motion transfer (1) object discovery (1) 3d object segmentation (1) generative model (1) world model (1) 3d point cloud (1) continuous normalizing flow (1) synthetic dataset (1) 3d semantic segmentation (1) distributional representation (1) crowded scene (1) real-world image (1) 3d instance segmentation (1) unsupervised semantic segmentation (1) object completion (1)

Papers

EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision CVPR 2026 PhysInOne: Visual Physics Learning and Reasoning in One Suite CVPR 2026 GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision ICLR 2025 LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds CVPR 2025 unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning ICML 2025 GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds CVPR 2023 Learning Flexibly Distributional Representation for Low-quality 3D Face Recognition AAAI 2021