CVAIGRAug 14, 2022

HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields

arXiv:2208.06787v253 citationsh-index: 33
Originality Incremental advance
AI Analysis

This addresses the challenge of creating HDR 3D scenes from real-world LDR images for applications in computer vision and graphics.

The paper tackles the problem of reconstructing high dynamic range (HDR) radiance fields from multi-view low dynamic range (LDR) images taken with varying camera settings, achieving detail and high-quality HDR novel views.

We propose high dynamic range (HDR) radiance fields, HDR-Plenoxels, that learn a plenoptic function of 3D HDR radiance fields, geometry information, and varying camera settings inherent in 2D low dynamic range (LDR) images. Our voxel-based volume rendering pipeline reconstructs HDR radiance fields with only multi-view LDR images taken from varying camera settings in an end-to-end manner and has a fast convergence speed. To deal with various cameras in real-world scenarios, we introduce a tone mapping module that models the digital in-camera imaging pipeline (ISP) and disentangles radiometric settings. Our tone mapping module allows us to render by controlling the radiometric settings of each novel view. Finally, we build a multi-view dataset with varying camera conditions, which fits our problem setting. Our experiments show that HDR-Plenoxels can express detail and high-quality HDR novel views from only LDR images with various cameras.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes