Diffusion-Promoted HDR Video Reconstruction

• URL: http://arxiv.org/abs/2406.08204v1
• Date: Wed, 12 Jun 2024 13:38:10 GMT
• Title: Diffusion-Promoted HDR Video Reconstruction
• Authors: Yuanshen Guan, Ruikang Xu, Mingde Yao, Ruisheng Gao, Lizhi Wang, Zhiwei Xiong,
• Abstract summary: High dynamic range (LDR) video reconstruction aims to generate HDR videos from low dynamic range (LDR) frames captured with alternating exposures. Most existing works solely rely on the regression-based paradigm, leading to adverse effects such as ghosting artifacts and missing details in saturated regions. We propose a diffusion-promoted method for HDR video reconstruction, termed HDR-V-Diff, which incorporates a diffusion model to capture the HDR distribution.
• Score: 45.73396977607666
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: High dynamic range (HDR) video reconstruction aims to generate HDR videos from low dynamic range (LDR) frames captured with alternating exposures. Most existing works solely rely on the regression-based paradigm, leading to adverse effects such as ghosting artifacts and missing details in saturated regions. In this paper, we propose a diffusion-promoted method for HDR video reconstruction, termed HDR-V-Diff, which incorporates a diffusion model to capture the HDR distribution. As such, HDR-V-Diff can reconstruct HDR videos with realistic details while alleviating ghosting artifacts. However, the direct introduction of video diffusion models would impose massive computational burden. Instead, to alleviate this burden, we first propose an HDR Latent Diffusion Model (HDR-LDM) to learn the distribution prior of single HDR frames. Specifically, HDR-LDM incorporates a tonemapping strategy to compress HDR frames into the latent space and a novel exposure embedding to aggregate the exposure information into the diffusion process. We then propose a Temporal-Consistent Alignment Module (TCAM) to learn the temporal information as a complement for HDR-LDM, which conducts coarse-to-fine feature alignment at different scales among video frames. Finally, we design a Zero-Init Cross-Attention (ZiCA) mechanism to effectively integrate the learned distribution prior and temporal information for generating HDR frames. Extensive experiments validate that HDR-V-Diff achieves state-of-the-art results on several representative datasets.

Related papers

• Exposure Completing for Temporally Consistent Neural High Dynamic Range Video Rendering [17.430726543786943]
  We propose a novel paradigm to render HDR frames via completing the absent exposure information. Our approach involves interpolating neighbor LDR frames in the time dimension to reconstruct LDR frames for the absent exposures. This benefits the fusing process for HDR results, reducing noise and ghosting artifacts therefore improving temporal consistency.
  arXiv  Detail & Related papers  (2024-07-18T09:13:08Z)
• 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)
• Exposure Diffusion: HDR Image Generation by Consistent LDR denoising [29.45922922270381]
  We seek inspiration from the HDR image capture literature that traditionally fuses sets of LDR images, called "brackets", to produce a single HDR image. We operate multiple denoising processes to generate multiple LDR brackets that together form a valid HDR result.
  arXiv  Detail & Related papers  (2024-05-23T08:24:22Z)
• 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)
• LAN-HDR: Luminance-based Alignment Network for High Dynamic Range Video Reconstruction [20.911738532410766]
  We propose an end-to-end HDR video composition framework, which aligns LDR frames in feature space and then merges aligned features into an HDR frame. In training, we adopt a temporal loss, in addition to frame reconstruction losses, to enhance temporal consistency and thus reduce flickering.
  arXiv  Detail & Related papers  (2023-08-22T01:43:00Z)
• 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)
• HDRVideo-GAN: Deep Generative HDR Video Reconstruction [19.837271879354184]
  We propose an end-to-end GAN-based framework for HDR video reconstruction from LDR sequences with alternating exposures. We first extract clean LDR frames from noisy LDR video with alternating exposures with a denoising network trained in a self-supervised setting. We then align the neighboring alternating-exposure frames to a reference frame and then reconstruct high-quality HDR frames in a complete adversarial setting.
  arXiv  Detail & Related papers  (2021-10-22T14:02:03Z)
• Beyond Visual Attractiveness: Physically Plausible Single Image HDR Reconstruction for Spherical Panoramas [60.24132321381606]
  We introduce the physical illuminance constraints to our single-shot HDR reconstruction framework. Our method can generate HDRs which are not only visually appealing but also physically plausible.
  arXiv  Detail & Related papers  (2021-03-24T01:51:19Z)
• 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.