Zehuan Huang

9 papers · 2024–2026 · 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 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16) 🏆 Keyword Champion (2)

Venues

CVPR (5) AAAI (2) ECCV (1) ICCV (1)

Top co-authors

Lu Sheng (7) Yan-Pei Cao (4) Junting Dong (2) Ding Liang (2) Yuan-Chen Guo (2) Xinyuan Chen (2) Yangguang Li (2) Bo Dai (2) Yifan Niu (2) Yaohui Wang (2)

Research topics

Computer Vision (7) Deep Learning (7) Generation (7) Models (7) Analysis (4) Artificial Intelligence (2) Machine Learning (2) Architectures (2) Core AI (2) Learning Paradigms (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Optimization & Theory (1)

Keywords

diffusion model (5) image generation (3) multi-view image generation (2) 3d reconstruction (2) multi-view generation (2) 3d scene generation (2) personalized generation (1) neural rendering (1) attention mechanism (1) dynamic routing (1) 3d vision (1) binocular vision (1) disparity estimation (1) 3d generation (1) neural radiance field (1) autoregressive generation (1) mixture of expert (1) world model (1) spatial coherence (1) text-to-image model (1)

Papers

InterMoE: Individual-Specific 3D Human Interaction Generation via Dynamic Temporal-Selective MoE AAAI 2026 Personalize Anything for Free with Diffusion Transformer AAAI 2026 Repurposing 3D Generative Model for Autoregressive Layout Generation CVPR 2026 Stereo World Model: Camera-Guided Stereo Video Generation CVPR 2026 MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation CVPR 2025 MV-Adapter: Multi-View Consistent Image Generation Made Easy ICCV 2025 Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion CVPR 2025 EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion CVPR 2024 Text to Layer-wise 3D Clothed Human Generation ECCV 2024