Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bemana, Mojtaba, Leimkühler, Thomas, Myszkowski, Karol, Seidel, Hans-Peter, Ritschel, Tobias
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916655665250304
author Bemana, Mojtaba
Leimkühler, Thomas
Myszkowski, Karol
Seidel, Hans-Peter
Ritschel, Tobias
author_facet Bemana, Mojtaba
Leimkühler, Thomas
Myszkowski, Karol
Seidel, Hans-Peter
Ritschel, Tobias
contents We demonstrate generating HDR images using the concerted action of multiple black-box, pre-trained LDR image diffusion models. Relying on a pre-trained LDR generative diffusion models is vital as, first, there is no sufficiently large HDR image dataset available to re-train them, and, second, even if it was, re-training such models is impossible for most compute budgets. Instead, we seek inspiration from the HDR image capture literature that traditionally fuses sets of LDR images, called "exposure brackets'', to produce a single HDR image. We operate multiple denoising processes to generate multiple LDR brackets that together form a valid HDR result. The key to making this work is to introduce a consistency term into the diffusion process to couple the brackets such that they agree across the exposure range they share while accounting for possible differences due to the quantization error. We demonstrate state-of-the-art unconditional and conditional or restoration-type (LDR2HDR) generative modeling results, yet in HDR.
format Preprint
id arxiv_https___arxiv_org_abs_2405_14304
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising
Bemana, Mojtaba
Leimkühler, Thomas
Myszkowski, Karol
Seidel, Hans-Peter
Ritschel, Tobias
Graphics
Computer Vision and Pattern Recognition
Image and Video Processing
We demonstrate generating HDR images using the concerted action of multiple black-box, pre-trained LDR image diffusion models. Relying on a pre-trained LDR generative diffusion models is vital as, first, there is no sufficiently large HDR image dataset available to re-train them, and, second, even if it was, re-training such models is impossible for most compute budgets. Instead, we seek inspiration from the HDR image capture literature that traditionally fuses sets of LDR images, called "exposure brackets'', to produce a single HDR image. We operate multiple denoising processes to generate multiple LDR brackets that together form a valid HDR result. The key to making this work is to introduce a consistency term into the diffusion process to couple the brackets such that they agree across the exposure range they share while accounting for possible differences due to the quantization error. We demonstrate state-of-the-art unconditional and conditional or restoration-type (LDR2HDR) generative modeling results, yet in HDR.
title Bracket Diffusion: HDR Image Generation by Consistent LDR Denoising
topic Graphics
Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2405.14304