paper-with-me

홈 › Papers

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

2022-08-14 · Kim Jun-Seong, Kim Yu-Ji, Moon Ye-Bin, Tae-Hyun Oh

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.

📄 PDF Abstract BibTeX arXiv:2208.06787

Code (1)

postech-ami/hdr-plenoxels 공식 구현 pytorch

Tasks

Tone MappingVocal Bursts Intensity Prediction

Similar Papers 제목 키워드 기반

Plenoxels: Radiance Fields without Neural Networks

2021-12-09 · CVPR 2022 1 · Alex Yu, Sara Fridovich-Keil, Matthew Tancik, Qinhong Chen 외

We introduce Plenoxels (plenoptic voxels), a system for photorealistic view synthesis. Plenoxels represent a scene as a sparse 3D grid with spherical harmonics. This representation can be optimized from calibrated images…

DPPE: Dense Pose Estimation in a Plenoxels Environment using Gradient Approximation

2024-03-16 · Christopher Kolios, Yeganeh Bahoo, Sajad Saeedi

We present DPPE, a dense pose estimation algorithm that functions over a Plenoxels environment. Recent advances in neural radiance field techniques have shown that it is a powerful tool for environment representation. Mo…

Neural RenderingPose EstimationTemplate Matching

Snapshot High Dynamic Range Imaging with a Polarization Camera

2023-08-16 · Mingyang Xie, Matthew Chan, Christopher Metzler

High dynamic range (HDR) images are important for a range of tasks, from navigation to consumer photography. Accordingly, a host of specialized HDR sensors have been developed, the most successful of which are based on c…

Physics-Informed Bayesian Learning of Electrohydrodynamic Polymer Jet Printing Dynamics

2022-04-16 · Athanasios Oikonomou, Theodoros Loutas, Dixia Fan, Alysia Garmulewicz 외

Calibration of highly dynamic multi-physics manufacturing processes such as electro-hydrodynamics-based additive manufacturing (AM) technologies (E-jet printing) is still performed by labor-intensive trial-and-error prac…

Ensemble models outperform single model uncertainties and predictions for operator-learning of hypersonic flows

2023-10-31 · Victor J. Leon, Noah Ford, Honest Mrema, Jeffrey Gilbert 외

High-fidelity computational simulations and physical experiments of hypersonic flows are resource intensive. Training scientific machine learning (SciML) models on limited high-fidelity data offers one approach to rapidl…

Operator learningUncertainty Quantification