PhysEditBench is a protocol-conditioned benchmark evaluating image editors on dense prediction of depth, normal, albedo, roughness, and metallic maps from RGB images using curated data and fixed scoring rules.
In: SIGGRAPH Asia 2022 Confer- ence Papers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2verdicts
UNVERDICTED 2representative citing papers
GaNI combines NeuS geometry reconstruction with a light-position-aware inverse neural radiosity stage that adds implicit near-field modeling, surface angle loss, and roughness smoothness priors to recover reflectance parameters from co-located light-camera captures.
citing papers explorer
-
PhysEditBench: A Protocol-Conditioned Benchmark for Dense Physical-Map Prediction with Image Editors
PhysEditBench is a protocol-conditioned benchmark evaluating image editors on dense prediction of depth, normal, albedo, roughness, and metallic maps from RGB images using curated data and fixed scoring rules.
-
GaNI: Global and Near Field Illumination Aware Neural Inverse Rendering
GaNI combines NeuS geometry reconstruction with a light-position-aware inverse neural radiosity stage that adds implicit near-field modeling, surface angle loss, and roughness smoothness priors to recover reflectance parameters from co-located light-camera captures.