NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-World Video Super-Resolution

• URL: http://arxiv.org/abs/2305.14669v3
• Date: Mon, 1 Jan 2024 14:40:33 GMT
• Title: NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-World Video Super-Resolution
• Authors: Yexing Song, Meilin Wang, Zhijing Yang, Xiaoyu Xian, Yukai Shi
• Abstract summary: Video super-resolution (VSR) to synthesize high-resolution (HR) video from ideal datasets has been demonstrated in many works. Applying VSR model to real-world video with unknown and complex degradation remains a challenging task. We propose a Negatives augmentation strategy for generalized noise modeling in Video Super-Resolution (NegVSR) task.
• Score: 12.103035018456566
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The capability of video super-resolution (VSR) to synthesize high-resolution (HR) video from ideal datasets has been demonstrated in many works. However, applying the VSR model to real-world video with unknown and complex degradation remains a challenging task. First, existing degradation metrics in most VSR methods are not able to effectively simulate real-world noise and blur. On the contrary, simple combinations of classical degradation are used for real-world noise modeling, which led to the VSR model often being violated by out-of-distribution noise. Second, many SR models focus on noise simulation and transfer. Nevertheless, the sampled noise is monotonous and limited. To address the aforementioned problems, we propose a Negatives augmentation strategy for generalized noise modeling in Video Super-Resolution (NegVSR) task. Specifically, we first propose sequential noise generation toward real-world data to extract practical noise sequences. Then, the degeneration domain is widely expanded by negative augmentation to build up various yet challenging real-world noise sets. We further propose the augmented negative guidance loss to learn robust features among augmented negatives effectively. Extensive experiments on real-world datasets (e.g., VideoLQ and FLIR) show that our method outperforms state-of-the-art methods with clear margins, especially in visual quality. Project page is available at: https://negvsr.github.io/.

Related papers

• From Chaos to Clarity: 3DGS in the Dark [28.232432162734437]
  Noise in unprocessed raw images compromises accuracy of 3D scene representation. 3D Gaussian Splatting (3DGS) is particularly susceptible to this noise. We introduce a novel self-supervised learning framework designed to reconstruct HDR 3DGS from noisy raw images.
  arXiv  Detail & Related papers  (2024-06-12T15:00:16Z)
• Realistic Noise Synthesis with Diffusion Models [68.48859665320828]
  Deep image denoising models often rely on large amount of training data for the high quality performance. We propose a novel method that synthesizes realistic noise using diffusion models, namely Realistic Noise Synthesize Diffusor (RNSD) RNSD can incorporate guided multiscale content, such as more realistic noise with spatial correlations can be generated at multiple frequencies.
  arXiv  Detail & Related papers  (2023-05-23T12:56:01Z)
• RViDeformer: Efficient Raw Video Denoising Transformer with a Larger Benchmark Dataset [16.131438855407175]
  There is no large dataset with realistic motions for supervised raw video denoising. We construct a video denoising dataset (named as ReCRVD) with 120 groups of noisy-clean videos. We propose an efficient raw video denoising transformer network (RViDeformer) that explores both short and long-distance correlations.
  arXiv  Detail & Related papers  (2023-05-01T11:06:58Z)
• PVDD: A Practical Video Denoising Dataset with Real-World Dynamic Scenes [56.4361151691284]
  "Practical Video Denoising dataset" (PVDD) contains 200 noisy-clean dynamic video pairs in both sRGB and RAW format. Compared with existing datasets consisting of limited motion information,PVDD covers dynamic scenes with varying natural motion.
  arXiv  Detail & Related papers  (2022-07-04T12:30:22Z)
• 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)
• Unsupervised Single Image Super-resolution Under Complex Noise [60.566471567837574]
  This paper proposes a model-based unsupervised SISR method to deal with the general SISR task with unknown degradations. The proposed method can evidently surpass the current state of the art (SotA) method (about 1dB PSNR) not only with a slighter model (0.34M vs. 2.40M) but also faster speed.
  arXiv  Detail & Related papers  (2021-07-02T11:55:40Z)
• Designing a Practical Degradation Model for Deep Blind Image Super-Resolution [134.9023380383406]
  Single image super-resolution (SISR) methods would not perform well if the assumed degradation model deviates from those in real images. This paper proposes to design a more complex but practical degradation model that consists of randomly shuffled blur, downsampling and noise degradations.
  arXiv  Detail & Related papers  (2021-03-25T17:40:53Z)
• CycleISP: Real Image Restoration via Improved Data Synthesis [166.17296369600774]
  We present a framework that models camera imaging pipeline in forward and reverse directions. By training a new image denoising network on realistic synthetic data, we achieve the state-of-the-art performance on real camera benchmark datasets.
  arXiv  Detail & Related papers  (2020-03-17T15:20:25Z)

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.