Unsupervised HDR Image and Video Tone Mapping via Contrastive Learning

Description

This project presents a unified framework (IVTMNet) for unsupervised image and video tone mapping, utilizing contrastive learning to improve the training process. It introduces a novel latent code to measure similarity between tone-mapped results and employs spatial-feature-enhanced and temporal-feature-replaced modules to enhance information exchange and temporal consistency. The project also provides a large-scale unpaired HDR-LDR video dataset, making it a valuable resource for developers working on HDR video tone mapping and related applications.

Resource details

Category path
Standards & Industry
Classification
Not yet classified

Unsupervised HDR Image and Video Tone Mapping via Contrastive Learning is cataloged in Standards & Industry. Its topics include HDR video, tone mapping, contrastive learning, unsupervised learning, and video processing.

URL

Tags

Related resources

  • Unsupervised HDR Tone Mapping via Contrastive LearningTCSVT 2023 academic paper with code (UnCLTMO) on unsupervised video HDR tone mapping with temporal consistency.
  • awesome-deep-hdrCurated list of deep-learning HDR imaging papers with accompanying code implementations.
  • tonemaplibPython library for video-focused HDR tone mapping, including a Reinhard02 implementation.
  • HDR ToolboxMATLAB/Octave toolbox with a broad collection of tone mapping operators (Reinhard, Durand, Mertens, etc.), widely cited in academia.