HumanOLAT is the first public full-body OLAT dataset: 21 subjects, 3 poses, 40 views, 331 single-light captures, plus environment maps, color gradients, meshes and normals.
Scal- ing in-the-wild training for diffusion-based illumination har- monization and editing by imposing consistent light trans- port
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
HumanOLAT: A Large-Scale Dataset for Full-Body Human Relighting and Novel-View Synthesis
HumanOLAT is the first public full-body OLAT dataset: 21 subjects, 3 poses, 40 views, 331 single-light captures, plus environment maps, color gradients, meshes and normals.