HDR Video Generation via Latent Alignment with Logarithmic Encoding

• URL: http://arxiv.org/abs/2604.11788v1
• Date: Mon, 13 Apr 2026 17:55:02 GMT
• Title: HDR Video Generation via Latent Alignment with Logarithmic Encoding
• Abstract summary: We demonstrate high-quality HDR video generation using a pretrained video model with minimal adaptation.<n>Our results indicate that HDR, despite representing a fundamentally different image formation regime, can be handled effectively without redesigning generative models.
• Score: 41.63873187838369
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: High dynamic range (HDR) imagery offers a rich and faithful representation of scene radiance, but remains challenging for generative models due to its mismatch with the bounded, perceptually compressed data on which these models are trained. A natural solution is to learn new representations for HDR, which introduces additional complexity and data requirements. In this work, we show that HDR generation can be achieved in a much simpler way by leveraging the strong visual priors already captured by pretrained generative models. We observe that a logarithmic encoding widely used in cinematic pipelines maps HDR imagery into a distribution that is naturally aligned with the latent space of these models, enabling direct adaptation via lightweight fine-tuning without retraining an encoder. To recover details that are not directly observable in the input, we further introduce a training strategy based on camera-mimicking degradations that encourages the model to infer missing high dynamic range content from its learned priors. Combining these insights, we demonstrate high-quality HDR video generation using a pretrained video model with minimal adaptation, achieving strong results across diverse scenes and challenging lighting conditions. Our results indicate that HDR, despite representing a fundamentally different image formation regime, can be handled effectively without redesigning generative models, provided that the representation is chosen to align with their learned priors.

Related papers

• Video Generation Models Are Inherent Lighting Estimators [54.44164570819254]
  Recent generation models can produce scenes with complex lighting, possessing an inherent understanding of lighting.<n>We introduce V-LITE (Video generation models are inherent lighting estimators), a framework that unlocks this internal knowledge by reframing estimation.<n>To bridge the gap from LDR-native models to the HDR domain, we design an HDR-aware VAE and employ an efficient LoRA-based fine-tuning strategy.
  arXiv  Detail & Related papers  (2026-07-06T04:59:17Z)
• HDR Image Reconstruction using an Unsupervised Fusion Model [0.0]
  High Dynamic Range (Exposure) imaging aims to reproduce the wide range of brightness levels present in natural scenes.<n>We propose a deep learning-based multi-exposure fusion approach for HDR image generation.
  arXiv  Detail & Related papers  (2025-10-21T17:43:22Z)
• LuxDiT: Lighting Estimation with Video Diffusion Transformer [66.60450792095901]
  Estimating scene lighting from a single image or video remains a longstanding challenge in computer vision and graphics.<n>We propose LuxDiT, a novel data-driven approach that fine-tunes a video diffusion transformer to generate HDR environment maps conditioned on visual input.
  arXiv  Detail & Related papers  (2025-09-03T19:59:20Z)
• LEDiff: Latent Exposure Diffusion for HDR Generation [11.669442066168244]
  LEDiff is a method that enables a generative model with HDR content generation through latent space exposure fusion techniques.<n>It also functions as an LDR-to- fusion converter, expanding the dynamic range of existing low-dynamic range images.
  arXiv  Detail & Related papers  (2024-12-19T02:15:55Z)
• Adapting Pretrained Networks for Image Quality Assessment on High Dynamic Range Displays [0.0]
  Conventional image quality metrics (IQMs) are designed for perceptually uniform gamma-encoded pixel values. Most of the available datasets consist of standard-dynamic-range (SDR) images collected in standard and possibly uncontrolled viewing conditions. Popular pre-trained neural networks are likewise intended for SDR inputs, restricting their direct application to HDR content. In this work, we explore more effective approaches for training deep learning-based models for image quality assessment (IQA) on HDR data.
  arXiv  Detail & Related papers  (2024-05-01T17:57:12Z)
• 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)
• 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)
• 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)
• Self-supervised HDR Imaging from Motion and Exposure Cues [14.57046548797279]
  We propose a novel self-supervised approach for learnable HDR estimation that alleviates the need for HDR ground-truth labels. Experimental results show that the HDR models trained using our proposed self-supervision approach achieve performance competitive with those trained under full supervision.
  arXiv  Detail & Related papers  (2022-03-23T10:22:03Z)

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.