zehuan-huang's picture

zehuan-huang

huanngzh

·

AI & ML interests

AIGC and 3D vision

Recent Activity

upvoted a paper about 17 hours ago

RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics

upvoted a paper 5 days ago

UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation

commented on a paper 5 days ago

UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation

View all activity

Organizations

Collections 2

Papers 7

arxiv:2503.12590

arxiv:2412.03558

arxiv:2412.03632

arxiv:2406.03184

spaces 1

Running on Zero

MV Adapter T2MV Anime

Generate anime-style multi-view images from texts

models 5

huanngzh/Ouroboros3D-SVD-LGM

Image-to-3D • Updated May 2 • 2

huanngzh/mv-adapter

Text-to-Image • Updated Mar 17 • 134k • 53

huanngzh/EpiDiff

Updated Jan 8 • 2

huanngzh/mvdream-sd2.1-diffusers

Text-to-Image • Updated Jul 25, 2024 • 1

huanngzh/Parts2Whole

Updated May 6, 2024 • 11 • 8

datasets 6

huanngzh/3D-Front

Preview • Updated Apr 27 • 2.26k • 2

huanngzh/Objaverse-Rand6View

Preview • Updated Apr 16 • 459 • 2

huanngzh/Objaverse-Ortho10View

Preview • Updated Apr 16 • 327 • 4

huanngzh/midi-page-assets

Updated Mar 11 • 1.52k

huanngzh/DeepFashion-MultiModal-Parts2Whole

Viewer • Updated May 26, 2024 • 41.5k • 141 • 7

huanngzh/anime_face_control_60k

Viewer • Updated Apr 7, 2023 • 60k • 26 • 4