Carview!

CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Sun, 23 Nov 2025 23:53:31 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"69239e7b-5d65" expires: Sun, 28 Dec 2025 11:24:30 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 2DBF:123DE:78556E:86EB1B:69511116 accept-ranges: bytes age: 0 date: Sun, 28 Dec 2025 11:14:30 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210032-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766920471.502166,VS0,VE219 vary: Accept-Encoding x-fastly-request-id: 6d39ab486e6f870984abb3db6f7bb117d494633d content-length: 5684 Hanwen Jiang

About me

I am a Research Scientist at Adobe Research. My works aim at expanding the scope of 3D Vision beyond its traditional boundaries. My philosophy is to approach research with a 3D mindset (worldview), while employing more non-3D techniques (methodology).

My goal is building scalable learning paradigms and models for spatially and physically grounded intelligence. Currently, I am interested in building 3D-aware and controllable world models (especially on representation learning) with self-supervision.

I received my Ph.D. in CS at UT Austin, honored to be advised by Prof. Qixing Huang and Prof. Georgios Pavlakos. I received an M.S. in CS from UCSD in 2021, fortunately advised by Prof. Xiaolong Wang.

Publications

RayZer: A Self-supervised Large View Synthesis Model

Hanwen Jiang, Hao Tan, Peng Wang, Haian Jin, Yue Zhao, Sai Bi, Kai Zhang, Fujun Luan, Kalyan Sunkavalli, Qixing Huang, Georgios Pavlakos

ICCV, 2025 (Best Student Paper Honorable Mention, Best Paper Candidate, Oral Presentation)

Hanwen Jiang 江翰文

About me

Publications

RayZer: A Self-supervised Large View Synthesis Model

Real3D: Scaling Up Large Reconstruction Models with Real-World Images

MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data

LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias

Atlas Gaussians Diffusion for 3D Generation

CoFie: Learning Compact Neural Surface Representations with Coordinate Fields

OmniGlue: Generalizable Feature Matching with Foundation Model Guidance

LEAP: Liberate Sparse-view 3D Modeling from Camera Poses

Doduo: Learning Dense Visual Correspondence from Unsupervised Semantic-Aware Flow

Few-View Object Reconstruction with Unknown Categories and Camera Poses

Single-Stage Visual Query Localization in Egocentric Videos

DexMV: Imitation Learning for Dexterous Manipulation from Human Videos

Hand-Object Contact Consistency Reasoning for Human Grasps Generation

Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time

Robust Lane Detection from Continuous Driving Scenes Using Deep Neural Networks

Talks

Towards Scalable 3D Reconstruction Models

RayZer: A Self-supervised Large View Synthesis Model

Service

Honors & Awards

Personal