Reconstructing 3D Scenes in Native High Dynamic Range
By: Kaixuan Zhang , Minxian Li , Mingwu Ren and more
Potential Business Impact:
Creates super-real 3D worlds from bright, detailed photos.
High Dynamic Range (HDR) imaging is essential for professional digital media creation, e.g., filmmaking, virtual production, and photorealistic rendering. However, 3D scene reconstruction has primarily focused on Low Dynamic Range (LDR) data, limiting its applicability to professional workflows. Existing approaches that reconstruct HDR scenes from LDR observations rely on multi-exposure fusion or inverse tone-mapping, which increase capture complexity and depend on synthetic supervision. With the recent emergence of cameras that directly capture native HDR data in a single exposure, we present the first method for 3D scene reconstruction that directly models native HDR observations. We propose {\bf Native High dynamic range 3D Gaussian Splatting (NH-3DGS)}, which preserves the full dynamic range throughout the reconstruction pipeline. Our key technical contribution is a novel luminance-chromaticity decomposition of the color representation that enables direct optimization from native HDR camera data. We demonstrate on both synthetic and real multi-view HDR datasets that NH-3DGS significantly outperforms existing methods in reconstruction quality and dynamic range preservation, enabling professional-grade 3D reconstruction directly from native HDR captures. Code and datasets will be made available.
Similar Papers
Casual3DHDR: Deblurring High Dynamic Range 3D Gaussian Splatting from Casually Captured Videos
CV and Pattern Recognition
Makes realistic 3D pictures from shaky videos.
GaussHDR: High Dynamic Range Gaussian Splatting via Learning Unified 3D and 2D Local Tone Mapping
CV and Pattern Recognition
Makes blurry pictures sharp and bright.
Mono4DGS-HDR: High Dynamic Range 4D Gaussian Splatting from Alternating-exposure Monocular Videos
CV and Pattern Recognition
Makes 3D videos look real with bright and dark colors.