LLM-HDR: Bridging LLM-based Perception and Self-Supervision for Unpaired LDR-to-HDR Image Reconstruction

• URL: http://arxiv.org/abs/2410.15068v2
• Date: Tue, 11 Mar 2025 06:46:42 GMT
• Title: LLM-HDR: Bridging LLM-based Perception and Self-Supervision for Unpaired LDR-to-HDR Image Reconstruction
• Authors: Hrishav Bakul Barua, Kalin Stefanov, Lemuel Lai En Che, Abhinav Dhall, KokSheik Wong, Ganesh Krishnasamy,
• Abstract summary: The paper proposes a method that integrates the perception of Large Language Models (LLM) into a modified semantic artifact-consistent adversarial architecture.<n>The method achieves state-of-the-art performance across several benchmark datasets and reconstructs high-quality HDR images.
• Score: 10.957314050894652
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The translation of Low Dynamic Range (LDR) to High Dynamic Range (HDR) images is an important computer vision task. There is a significant amount of research utilizing both conventional non-learning methods and modern data-driven approaches, focusing on using both single-exposed and multi-exposed LDR for HDR image reconstruction. However, most current state-of-the-art methods require high-quality paired {LDR,HDR} datasets for model training. In addition, there is limited literature on using unpaired datasets for this task, that is, the model learns a mapping between domains, i.e., {LDR,HDR}. This paper proposes LLM-HDR, a method that integrates the perception of Large Language Models (LLM) into a modified semantic- and cycle-consistent adversarial architecture that utilizes unpaired {LDR,HDR} datasets for training. The method introduces novel artifact- and exposure-aware generators to address visual artifact removal and an encoder and loss to address semantic consistency, another under-explored topic. LLM-HDR is the first to use an LLM for the {LDR,HDR} translation task in a self-supervised setup. The method achieves state-of-the-art performance across several benchmark datasets and reconstructs high-quality HDR images. The official website of this work is available at: https://github.com/HrishavBakulBarua/LLM-HDR

Related papers

• iHDR: Iterative HDR Imaging with Arbitrary Number of Exposures [1.9686770963118383]
  High dynamic range (LDR) imaging aims to obtain a high-quality HDR image by fusing information from multiple low dynamic range (LDR) images.<n>Our framework comprises a ghost-free Dual-input fusion network (Di) and a physics-based domain mapping network (ToneNet)<n>Di estimates an intermediate HDR image, while ToneNet maps it back to the nonlinear domain and serves as the reference for the next pairwise fusion.
  arXiv  Detail & Related papers  (2025-05-29T01:20:31Z)
• HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting [76.5908492298286]
  Existing HDR NVS methods are mainly based on NeRF. They suffer from long training time and slow inference speed. We propose a new framework, High Dynamic Range Gaussian Splatting (-GS)
  arXiv  Detail & Related papers  (2024-05-24T00:46:58Z)
• Generating Content for HDR Deghosting from Frequency View [56.103761824603644]
  Recent Diffusion Models (DMs) have been introduced in HDR imaging field. DMs require extensive iterations with large models to estimate entire images. We propose the Low-Frequency aware Diffusion (LF-Diff) model for ghost-free HDR imaging.
  arXiv  Detail & Related papers  (2024-04-01T01:32:11Z)
• HistoHDR-Net: Histogram Equalization for Single LDR to HDR Image Translation [12.45632443397018]
  High Dynamic Range ( HDR) imaging aims to replicate the high visual quality and clarity of real-world scenes. The literature offers various data-driven methods for HDR image reconstruction from Low Dynamic Range (LDR) counterparts. A common limitation of these approaches is missing details in regions of the reconstructed HDR images. We propose a simple and effective method, Histo-Net, to recover the fine details.
  arXiv  Detail & Related papers  (2024-02-08T20:14:46Z)
• Towards High-quality HDR Deghosting with Conditional Diffusion Models [88.83729417524823]
  High Dynamic Range (LDR) images can be recovered from several Low Dynamic Range (LDR) images by existing Deep Neural Networks (DNNs) techniques. DNNs still generate ghosting artifacts when LDR images have saturation and large motion. We formulate the HDR deghosting problem as an image generation that leverages LDR features as the diffusion model's condition.
  arXiv  Detail & Related papers  (2023-11-02T01:53:55Z)
• Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes [58.66427721308464]
  Self is a self-supervised reconstruction method that only requires dynamic multi-exposure images during training. Self achieves superior results against the state-of-the-art self-supervised methods, and comparable performance to supervised ones.
  arXiv  Detail & Related papers  (2023-10-03T07:10:49Z)
• Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction [23.930923461672894]
  LDR stack-based methods are used for single-image HDR reconstruction, generating an HDR image from a deep learning-generated LDR stack. Current methods generate the stack with predetermined exposure values (EVs), which may limit the quality of HDR reconstruction. We propose the continuous exposure value representation (CEVR), which uses an implicit function to generate LDR images with arbitrary EVs.
  arXiv  Detail & Related papers  (2023-09-07T17:59:03Z)
• SMAE: Few-shot Learning for HDR Deghosting with Saturation-Aware Masked Autoencoders [97.64072440883392]
  We propose a novel semi-supervised approach to realize few-shot HDR imaging via two stages of training, called SSHDR. Unlikely previous methods, directly recovering content and removing ghosts simultaneously, which is hard to achieve optimum. Experiments demonstrate that SSHDR outperforms state-of-the-art methods quantitatively and qualitatively within and across different datasets.
  arXiv  Detail & Related papers  (2023-04-14T03:42:51Z)
• HDR Video Reconstruction with a Large Dynamic Dataset in Raw and sRGB Domains [23.309488653045026]
  High dynamic range ( HDR) video reconstruction is attracting more and more attention due to the superior visual quality compared with those of low dynamic range (LDR) videos. There are still no real LDR- pairs for dynamic scenes due to the difficulty in capturing LDR- frames simultaneously. In this work, we propose to utilize a staggered sensor to capture two alternate exposure images simultaneously, which are then fused into an HDR frame in both raw and sRGB domains.
  arXiv  Detail & Related papers  (2023-04-10T11:59:03Z)
• GlowGAN: Unsupervised Learning of HDR Images from LDR Images in the Wild [74.52723408793648]
  We present the first method for learning a generative model of HDR images from in-the-wild LDR image collections in a fully unsupervised manner. The key idea is to train a generative adversarial network (GAN) to generate HDR images which, when projected to LDR under various exposures, are indistinguishable from real LDR images. Experiments show that our method GlowGAN can synthesize photorealistic HDR images in many challenging cases such as landscapes, lightning, or windows.
  arXiv  Detail & Related papers  (2022-11-22T15:42:08Z)
• A Two-stage Deep Network for High Dynamic Range Image Reconstruction [0.883717274344425]
  This study tackles the challenges of single-shot LDR to HDR mapping by proposing a novel two-stage deep network. Notably, our proposed method aims to reconstruct an HDR image without knowing hardware information, including camera response function (CRF) and exposure settings.
  arXiv  Detail & Related papers  (2021-04-19T15:19:17Z)
• HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset [30.249052175655606]
  We introduce a coarse-to-fine deep learning framework for HDR video reconstruction. Firstly, we perform coarse alignment and pixel blending in the image space to estimate the coarse HDR video. Secondly, we conduct more sophisticated alignment and temporal fusion in the feature space of the coarse HDR video to produce better reconstruction.
  arXiv  Detail & Related papers  (2021-03-27T16:40:05Z)
• MetaHDR: Model-Agnostic Meta-Learning for HDR Image Reconstruction [0.0]
  Existing approaches for converting low dynamic range images to high dynamic range images are limited by the assumption that all conversions are governed by the same nonlinear mapping. We propose "Meta-Learning for HDR-Agnostic Image Reconstruction" (Meta), which applies meta-learning to the LDR-to-Model conversion problem using existing HDR datasets.
  arXiv  Detail & Related papers  (2021-03-20T07:56:45Z)
• HDR-GAN: HDR Image Reconstruction from Multi-Exposed LDR Images with Large Motions [62.44802076971331]
  We propose a novel GAN-based model, HDR-GAN, for synthesizing HDR images from multi-exposed LDR images. By incorporating adversarial learning, our method is able to produce faithful information in the regions with missing content.
  arXiv  Detail & Related papers  (2020-07-03T11:42:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.