paper-with-me

Papers

ViStripformer: A Token-Efficient Transformer for Versatile Video Restoration

2023-12-22 · Fu-Jen Tsai, Yan-Tsung Peng, Chen-Yu Chang, Chan-Yu Li, Yen-Yu Lin, Chung-Chi Tsai, Chia-Wen Lin

Video restoration is a low-level vision task that seeks to restore clean, sharp videos from quality-degraded frames. One would use the temporal information from adjacent frames to make video restoration successful. Recently, the success of the Transformer has raised awareness in the computer-vision community. However, its self-attention mechanism requires much memory, which is unsuitable for high-resolution vision tasks like video restoration. In this paper, we propose ViStripformer (Video Stripformer), which utilizes spatio-temporal strip attention to catch long-range data correlations, consisting of intra-frame strip attention (Intra-SA) and inter-frame strip attention (Inter-SA) for extracting spatial and temporal information. It decomposes video frames into strip-shaped features in horizontal and vertical directions for Intra-SA and Inter-SA to address degradation patterns with various orientations and magnitudes. Besides, ViStripformer is an effective and efficient transformer architecture with much lower memory usage than the vanilla transformer. Extensive experiments show that the proposed model achieves superior results with fast inference time on video restoration tasks, including video deblurring, demoireing, and deraining.

📄 PDF Abstract BibTeX arXiv:2312.14502

Code (1)

pp00704831/video-stripformer 공식 구현 pytorch

Tasks

DeblurringRain RemovalVideo DeblurringVideo Restoration

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Position-Wise Feed-Forward Layer 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

DiffIR2VR-Zero: Zero-Shot Video Restoration with Diffusion-based Image Restoration Models

2024-07-01 · Chang-Han Yeh, Chin-Yang Lin, Zhixiang Wang, Chi-Wei Hsiao 외

This paper introduces a method for zero-shot video restoration using pre-trained image restoration diffusion models. Traditional video restoration methods often need retraining for different settings and struggle with li…

DenoisingImage RestorationOptical Flow EstimationSuper-Resolution+3

DiTVR: Zero-Shot Diffusion Transformer for Video Restoration

2025-08-11 · Sicheng Gao, Nancy Mehta, Zongwei Wu, Radu Timofte arxiv

Video restoration aims to reconstruct high quality video sequences from low quality inputs, addressing tasks such as super resolution, denoising, and deblurring. Traditional regression based methods often produce unreali…

Video Restoration

V-Bridge: Bridging Video Generative Priors to Versatile Few-shot Image Restoration

2026-03-13 · Shenghe Zheng, Junpeng Jiang, Wenbo Li arxiv

Large-scale video generative models are trained on vast and diverse visual data, enabling them to internalize rich structural, semantic, and dynamic priors of the visual world. While these models have demonstrated impres…

Image Restoration

AsymRnR: Video Diffusion Transformers Acceleration with Asymmetric Reduction and Restoration

2024-12-16 · Wenhao Sun, Rong-Cheng Tu, Jingyi Liao, Zhao Jin 외

Video Diffusion Transformers (DiTs) have demonstrated significant potential for generating high-fidelity videos but are computationally intensive. Existing acceleration methods include distillation, which requires costly…

DenoisingToken Reduction

MR-VNet: Media Restoration using Volterra Networks

2024-01-01 · CVPR 2024 1 · Siddharth Roheda, Amit Unde, Loay Rashid

This research paper presents a novel class of restoration network architecture based on the Volterra series formulation. By incorporating non-linearity into the system response function through higher order convoluti…

Image DeblurringVideo Restoration