AI RESEARCH
HDR 3D Gaussian Splatting via Luminance-Chromaticity Decomposition
arXiv CS.CV
•
ArXi:2511.12895v2 Announce Type: replace High Dynamic Range (HDR) 3D reconstruction is pivotal for professional content creation in filmmaking and virtual production. Existing methods typically rely on multi-exposure Low Dynamic Range (LDR) supervision to constrain the learning process within vast brightness spaces, resulting in complex, dual-branch architectures. This work explores the feasibility of learning HDR 3D models exclusively in the HDR data space to simplify model design.