CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Tue, 11 Feb 2025 23:11:37 GMT access-control-allow-origin: * strict-transport-security: max-age=31556952 etag: W/"67abd929-65ec" expires: Tue, 30 Dec 2025 09:28:01 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 8C4C:21D6A4:9F15B0:B2897A:695398C9 accept-ranges: bytes age: 0 date: Tue, 30 Dec 2025 09:18:01 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210055-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1767086281.471034,VS0,VE212 vary: Accept-Encoding x-fastly-request-id: 45ff1f016ff9bb6ed7c32e089ebb214e41af2a52 content-length: 3860 RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

RelitLRM: Generative Relightable Radiance for Large Reconstruction Models

Tianyuan Zhang ¹, Zhengfei Kuang², Haian Jin³, Zexiang Xu⁴, Sai Bi⁴, Hao Tan⁴, He Zhang⁴, Yiwei Hu⁴, Milos Hasan⁴, William T. Freeman¹, Kai Zhang^*4, Fujun Luan^*4 ^*(Equal Advising)
¹ Massachusetts Institute of Technology ²Stanford University ³Cornell University ⁴Adobe Research
ICLR, 2025 (Spotlight)

A Diffusion Transformer that tries to learn the underlying physics of reconstruction and rendering. It autonomously learns shadow casting, specular highlights, and inter-reflections, though not as precise as ray-tracing, but all neurally learned.