Jointly relighting all input views with a multiview diffusion model, then fitting a radiance field with per-image shading embeddings, reconstructs specular 3D objects from inconsistently lit photos better than prior methods.
Align your latents: High-resolution video synthesis with la- tent diffusion models
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
2024 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Generative Multiview Relighting for 3D Reconstruction under Extreme Illumination Variation
Jointly relighting all input views with a multiview diffusion model, then fitting a radiance field with per-image shading embeddings, reconstructs specular 3D objects from inconsistently lit photos better than prior methods.