Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting

• URL: http://arxiv.org/abs/2303.08331v2
• Date: Sun, 18 Jun 2023 15:29:37 GMT
• Title: Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting
• Authors: Gen Li, Jie Ji, Minghai Qin, Wei Niu, Bin Ren, Fatemeh Afghah, Linke Guo, Xiaolong Ma
• Abstract summary: Deep convolutional neural networks (DNNs) are widely used in various fields of computer vision. We propose a novel method for high-quality and efficient video resolution upscaling tasks. We deploy our models on an off-the-shelf mobile phone, and experimental results show that our method achieves real-time video super-resolution with high video quality.
• Score: 27.302681897961588
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As deep convolutional neural networks (DNNs) are widely used in various fields of computer vision, leveraging the overfitting ability of the DNN to achieve video resolution upscaling has become a new trend in the modern video delivery system. By dividing videos into chunks and overfitting each chunk with a super-resolution model, the server encodes videos before transmitting them to the clients, thus achieving better video quality and transmission efficiency. However, a large number of chunks are expected to ensure good overfitting quality, which substantially increases the storage and consumes more bandwidth resources for data transmission. On the other hand, decreasing the number of chunks through training optimization techniques usually requires high model capacity, which significantly slows down execution speed. To reconcile such, we propose a novel method for high-quality and efficient video resolution upscaling tasks, which leverages the spatial-temporal information to accurately divide video into chunks, thus keeping the number of chunks as well as the model size to minimum. Additionally, we advance our method into a single overfitting model by a data-aware joint training technique, which further reduces the storage requirement with negligible quality drop. We deploy our models on an off-the-shelf mobile phone, and experimental results show that our method achieves real-time video super-resolution with high video quality. Compared with the state-of-the-art, our method achieves 28 fps streaming speed with 41.6 PSNR, which is 14$\times$ faster and 2.29 dB better in the live video resolution upscaling tasks. Code available in https://github.com/coulsonlee/STDO-CVPR2023.git

Related papers

• EPS: Efficient Patch Sampling for Video Overfitting in Deep Super-Resolution Model Training [15.684865589513597]
  We propose an efficient patch sampling method named EPS for video SR network overfitting. Our method reduces the number of patches for the training to 4% to 25%, depending on the resolution and number of clusters. Compared to the state-of-the-art patch sampling method, EMT, our approach achieves an 83% decrease in overall run time.
  arXiv  Detail & Related papers  (2024-11-25T12:01:57Z)
• Adaptive Caching for Faster Video Generation with Diffusion Transformers [52.73348147077075]
  Diffusion Transformers (DiTs) rely on larger models and heavier attention mechanisms, resulting in slower inference speeds. We introduce a training-free method to accelerate video DiTs, termed Adaptive Caching (AdaCache) We also introduce a Motion Regularization (MoReg) scheme to utilize video information within AdaCache, controlling the compute allocation based on motion content.
  arXiv  Detail & Related papers  (2024-11-04T18:59:44Z)
• Data Overfitting for On-Device Super-Resolution with Dynamic Algorithm and Compiler Co-Design [18.57172631588624]
  We propose a Dynamic Deep neural network assisted by a Content-Aware data processing pipeline to reduce the model number down to one. Our method achieves better PSNR and real-time performance (33 FPS) on an off-the-shelf mobile phone.
  arXiv  Detail & Related papers  (2024-07-03T05:17:26Z)
• Hierarchical Patch Diffusion Models for High-Resolution Video Generation [50.42746357450949]
  We develop deep context fusion, which propagates context information from low-scale to high-scale patches in a hierarchical manner. We also propose adaptive computation, which allocates more network capacity and computation towards coarse image details. The resulting model sets a new state-of-the-art FVD score of 66.32 and Inception Score of 87.68 in class-conditional video generation.
  arXiv  Detail & Related papers  (2024-06-12T01:12:53Z)
• Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition [124.41196697408627]
  We propose content-motion latent diffusion model (CMD), a novel efficient extension of pretrained image diffusion models for video generation. CMD encodes a video as a combination of a content frame (like an image) and a low-dimensional motion latent representation. We generate the content frame by fine-tuning a pretrained image diffusion model, and we generate the motion latent representation by training a new lightweight diffusion model.
  arXiv  Detail & Related papers  (2024-03-21T05:48:48Z)
• A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames [54.90226700939778]
  We build on the common paradigm of transferring large-scale, image--text models to video via shallow temporal fusion. We expose two limitations to the approach: (1) decreased spatial capabilities, likely due to poor video--language alignment in standard video datasets, and (2) higher memory consumption, bottlenecking the number of frames that can be processed.
  arXiv  Detail & Related papers  (2023-12-12T16:10:19Z)
• AsConvSR: Fast and Lightweight Super-Resolution Network with Assembled Convolutions [32.85522513271578]
  We propose a fast and lightweight super-resolution network to achieve real-time performance. By analyzing the applications of divide-and-conquer in super-resolution, we propose assembled convolutions which can adapt convolution kernels according to the input features. Our method also wins the first place in NTIRE 2023 Real-Time Super-Resolution - Track 1.
  arXiv  Detail & Related papers  (2023-05-05T09:33:34Z)
• HNeRV: A Hybrid Neural Representation for Videos [56.492309149698606]
  Implicit neural representations store videos as neural networks. We propose a Hybrid Neural Representation for Videos (HNeRV) With content-adaptive embeddings and re-designed architecture, HNeRV outperforms implicit methods in video regression tasks.
  arXiv  Detail & Related papers  (2023-04-05T17:55:04Z)
• Leveraging Bitstream Metadata for Fast, Accurate, Generalized Compressed Video Quality Enhancement [74.1052624663082]
  We develop a deep learning architecture capable of restoring detail to compressed videos. We show that this improves restoration accuracy compared to prior compression correction methods. We condition our model on quantization data which is readily available in the bitstream.
  arXiv  Detail & Related papers  (2022-01-31T18:56:04Z)
• Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation [38.889823516049056]
  Methods divide a video into chunks, and stream LR video chunks and corresponding content-aware models to the client. With our method, each video chunk only requires less than $1% $ of original parameters to be streamed, achieving even better SR performance.
  arXiv  Detail & Related papers  (2021-08-18T15:34:11Z)

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.