LEDiff: Latent Exposure Diffusion for HDR Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Chao, Xia, Zhihao, Leimkuehler, Thomas, Myszkowski, Karol, Zhang, Xuaner
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910773329002496
author Wang, Chao
Xia, Zhihao
Leimkuehler, Thomas
Myszkowski, Karol
Zhang, Xuaner
author_facet Wang, Chao
Xia, Zhihao
Leimkuehler, Thomas
Myszkowski, Karol
Zhang, Xuaner
contents While consumer displays increasingly support more than 10 stops of dynamic range, most image assets such as internet photographs and generative AI content remain limited to 8-bit low dynamic range (LDR), constraining their utility across high dynamic range (HDR) applications. Currently, no generative model can produce high-bit, high-dynamic range content in a generalizable way. Existing LDR-to-HDR conversion methods often struggle to produce photorealistic details and physically-plausible dynamic range in the clipped areas. We introduce LEDiff, a method that enables a generative model with HDR content generation through latent space fusion inspired by image-space exposure fusion techniques. It also functions as an LDR-to-HDR converter, expanding the dynamic range of existing low-dynamic range images. Our approach uses a small HDR dataset to enable a pretrained diffusion model to recover detail and dynamic range in clipped highlights and shadows. LEDiff brings HDR capabilities to existing generative models and converts any LDR image to HDR, creating photorealistic HDR outputs for image generation, image-based lighting (HDR environment map generation), and photographic effects such as depth of field simulation, where linear HDR data is essential for realistic quality.
format Preprint
id arxiv_https___arxiv_org_abs_2412_14456
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LEDiff: Latent Exposure Diffusion for HDR Generation
Wang, Chao
Xia, Zhihao
Leimkuehler, Thomas
Myszkowski, Karol
Zhang, Xuaner
Computer Vision and Pattern Recognition
Image and Video Processing
While consumer displays increasingly support more than 10 stops of dynamic range, most image assets such as internet photographs and generative AI content remain limited to 8-bit low dynamic range (LDR), constraining their utility across high dynamic range (HDR) applications. Currently, no generative model can produce high-bit, high-dynamic range content in a generalizable way. Existing LDR-to-HDR conversion methods often struggle to produce photorealistic details and physically-plausible dynamic range in the clipped areas. We introduce LEDiff, a method that enables a generative model with HDR content generation through latent space fusion inspired by image-space exposure fusion techniques. It also functions as an LDR-to-HDR converter, expanding the dynamic range of existing low-dynamic range images. Our approach uses a small HDR dataset to enable a pretrained diffusion model to recover detail and dynamic range in clipped highlights and shadows. LEDiff brings HDR capabilities to existing generative models and converts any LDR image to HDR, creating photorealistic HDR outputs for image generation, image-based lighting (HDR environment map generation), and photographic effects such as depth of field simulation, where linear HDR data is essential for realistic quality.
title LEDiff: Latent Exposure Diffusion for HDR Generation
topic Computer Vision and Pattern Recognition
Image and Video Processing
url https://arxiv.org/abs/2412.14456