Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approach

• URL: http://arxiv.org/abs/2211.03058v1
• Date: Sun, 6 Nov 2022 08:27:37 GMT
• Title: Towards Real World HDRTV Reconstruction: A Data Synthesis-based Approach
• Authors: Zhen Cheng, Tao Wang, Yong Li, Fenglong Song, Chang Chen, Zhiwei Xiong
• Abstract summary: Existing deep learning based HDRTV reconstruction methods assume one kind of tone mapping operators (TMOs) as the procedure to synthesize SDRTV-TV pairs for supervised training. In this paper, we argue that, although traditional TMOs exploit efficient dynamic range compression priors, they have several drawbacks on modeling the degradation information over-preservation, color bias and possible artifacts. We propose a learning-based data synthesis approach to learn the properties of real-world SDRTVs by integrating several tone mapping priors into both network structures and loss functions.
• Score: 48.1492764654516
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Existing deep learning based HDRTV reconstruction methods assume one kind of tone mapping operators (TMOs) as the degradation procedure to synthesize SDRTV-HDRTV pairs for supervised training. In this paper, we argue that, although traditional TMOs exploit efficient dynamic range compression priors, they have several drawbacks on modeling the realistic degradation: information over-preservation, color bias and possible artifacts, making the trained reconstruction networks hard to generalize well to real-world cases. To solve this problem, we propose a learning-based data synthesis approach to learn the properties of real-world SDRTVs by integrating several tone mapping priors into both network structures and loss functions. In specific, we design a conditioned two-stream network with prior tone mapping results as a guidance to synthesize SDRTVs by both global and local transformations. To train the data synthesis network, we form a novel self-supervised content loss to constraint different aspects of the synthesized SDRTVs at regions with different brightness distributions and an adversarial loss to emphasize the details to be more realistic. To validate the effectiveness of our approach, we synthesize SDRTV-HDRTV pairs with our method and use them to train several HDRTV reconstruction networks. Then we collect two inference datasets containing both labeled and unlabeled real-world SDRTVs, respectively. Experimental results demonstrate that, the networks trained with our synthesized data generalize significantly better to these two real-world datasets than existing solutions.

Related papers

• Beyond Feature Mapping GAP: Integrating Real HDRTV Priors for Superior SDRTV-to-HDRTV Conversion [22.78096367667505]
  The rise of HDR-WCG display devices has highlighted the need to convert SDRTV to HDRTV. Existing methods primarily focus on designing neural networks to learn a single-style mapping from SDRTV to HDRTV. We propose a novel method for SDRTV to HDRTV conversion guided by real HDRTV priors.
  arXiv  Detail & Related papers  (2024-11-16T11:20:29Z)
• Towards Realistic Data Generation for Real-World Super-Resolution [58.88039242455039]
  RealDGen is an unsupervised learning data generation framework designed for real-world super-resolution. We develop content and degradation extraction strategies, which are integrated into a novel content-degradation decoupled diffusion model. Experiments demonstrate that RealDGen excels in generating large-scale, high-quality paired data that mirrors real-world degradations.
  arXiv  Detail & Related papers  (2024-06-11T13:34:57Z)
• DeblurDiNAT: A Generalizable Transformer for Perceptual Image Deblurring [1.5124439914522694]
  DeblurDiNAT is a generalizable and efficient encoder-decoder Transformer which restores clean images visually close to the ground truth. We present a linear feed-forward network and a non-linear dual-stage feature fusion module for faster feature propagation across the network.
  arXiv  Detail & Related papers  (2024-03-19T21:31:31Z)
• Expanding Synthetic Real-World Degradations for Blind Video Super Resolution [3.474523163017713]
  Video super-resolution (VSR) techniques have drastically improved over the last few years and shown impressive performance on synthetic data. However, their performance on real-world video data suffers because of the complexity of real-world degradations and misaligned video frames. In this paper, we propose real-world degradations on synthetic training datasets.
  arXiv  Detail & Related papers  (2023-05-04T08:58:31Z)
• Benchmark Dataset and Effective Inter-Frame Alignment for Real-World Video Super-Resolution [65.20905703823965]
  Video super-resolution (VSR) aiming to reconstruct a high-resolution (HR) video from its low-resolution (LR) counterpart has made tremendous progress in recent years. It remains challenging to deploy existing VSR methods to real-world data with complex degradations. EAVSR takes the proposed multi-layer adaptive spatial transform network (MultiAdaSTN) to refine the offsets provided by the pre-trained optical flow estimation network.
  arXiv  Detail & Related papers  (2022-12-10T17:41:46Z)
• Learning Detail-Structure Alternative Optimization for Blind Super-Resolution [69.11604249813304]
  We propose an effective and kernel-free network, namely DSSR, which enables recurrent detail-structure alternative optimization without blur kernel prior incorporation for blind SR. In our DSSR, a detail-structure modulation module (DSMM) is built to exploit the interaction and collaboration of image details and structures. Our method achieves the state-of-the-art against existing methods.
  arXiv  Detail & Related papers  (2022-12-03T14:44:17Z)
• The Best of Both Worlds: a Framework for Combining Degradation Prediction with High Performance Super-Resolution Networks [14.804000317612305]
  We present a framework for combining blind SR prediction mechanism with any deep SR network. We show that our hybrid models consistently achieve stronger SR performance than both their non-blind and blind counterparts.
  arXiv  Detail & Related papers  (2022-11-09T16:49:35Z)
• Transformer-based SAR Image Despeckling [53.99620005035804]
  We introduce a transformer-based network for SAR image despeckling. The proposed despeckling network comprises of a transformer-based encoder which allows the network to learn global dependencies between different image regions. Experiments show that the proposed method achieves significant improvements over traditional and convolutional neural network-based despeckling methods.
  arXiv  Detail & Related papers  (2022-01-23T20:09:01Z)
• Investigating Tradeoffs in Real-World Video Super-Resolution [90.81396836308085]
  Real-world video super-resolution (VSR) models are often trained with diverse degradations to improve generalizability. To alleviate the first tradeoff, we propose a degradation scheme that reduces up to 40% of training time without sacrificing performance. To facilitate fair comparisons, we propose the new VideoLQ dataset, which contains a large variety of real-world low-quality video sequences.
  arXiv  Detail & Related papers  (2021-11-24T18:58:21Z)
• Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data [17.529045507657944]
  We extend the powerful ESRGAN to a practical restoration application (namely, Real-ESRGAN) A high-order degradation modeling process is introduced to better simulate complex real-world degradations. We also consider the common ringing and overshoot artifacts in the synthesis process.
  arXiv  Detail & Related papers  (2021-07-22T17:43:24Z)

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.