March 22, 2024, 4:46 a.m. | Peter Kocsis (Technical University of Munich), Vincent Sitzmann (MIT EECS), Matthias Nie{\ss}ner (Technical University of Munich)

cs.CV updates on arXiv.org arxiv.org

arXiv:2312.12274v2 Announce Type: replace
Abstract: We present Intrinsic Image Diffusion, a generative model for appearance decomposition of indoor scenes. Given a single input view, we sample multiple possible material explanations represented as albedo, roughness, and metallic maps. Appearance decomposition poses a considerable challenge in computer vision due to the inherent ambiguity between lighting and material properties and the lack of real datasets. To address this issue, we advocate for a probabilistic formulation, where instead of attempting to directly predict the …

abstract arxiv challenge computer computer vision cs.ai cs.cv cs.gr diffusion generative image image diffusion intrinsic maps material multiple sample type view vision

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Lead GNSS Data Scientist

@ Lurra Systems | Melbourne

Senior Machine Learning Engineer (MLOps)

@ Promaton | Remote, Europe

Principal Applied Scientist

@ Microsoft | Redmond, Washington, United States

Data Analyst / Action Officer

@ OASYS, INC. | OASYS, INC., Pratt Avenue Northwest, Huntsville, AL, United States