paper-with-me

Papers

Binarized Diffusion Model for Image Super-Resolution

2024-06-09 · Zheng Chen, Haotong Qin, Yong Guo, Xiongfei Su, Xin Yuan, Linghe Kong, Yulun Zhang

Advanced diffusion models (DMs) perform impressively in image super-resolution (SR), but the high memory and computational costs hinder their deployment. Binarization, an ultra-compression algorithm, offers the potential for effectively accelerating DMs. Nonetheless, due to the model structure and the multi-step iterative attribute of DMs, existing binarization methods result in significant performance degradation. In this paper, we introduce a novel binarized diffusion model, BI-DiffSR, for image SR. First, for the model structure, we design a UNet architecture optimized for binarization. We propose the consistent-pixel-downsample (CP-Down) and consistent-pixel-upsample (CP-Up) to maintain dimension consistent and facilitate the full-precision information transfer. Meanwhile, we design the channel-shuffle-fusion (CS-Fusion) to enhance feature fusion in skip connection. Second, for the activation difference across timestep, we design the timestep-aware redistribution (TaR) and activation function (TaA). The TaR and TaA dynamically adjust the distribution of activations based on different timesteps, improving the flexibility and representation alability of the binarized module. Comprehensive experiments demonstrate that our BI-DiffSR outperforms existing binarization methods. Code is released at: https://github.com/zhengchen1999/BI-DiffSR.

📄 PDF Abstract BibTeX arXiv:2406.05723

Code (1)

zhengchen1999/bi-diffsr 공식 구현 pytorch

Tasks

AttributeBinarizationImage Super-ResolutionmodelSuper-ResolutionTAR

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Efficient Super Resolution Using Binarized Neural Network

2018-12-16 · Yinglan Ma, Hongyu Xiong, Zhe Hu, Lizhuang Ma

Deep convolutional neural networks (DCNNs) have recently demonstrated high-quality results in single-image super-resolution (SR). DCNNs often suffer from over-parametrization and large amounts of redundancy, which result…

Binarizationimage-classificationImage ClassificationImage Enhancement+3

E2FIF: Push the limit of Binarized Deep Imagery Super-resolution using End-to-end Full-precision Information Flow

2022-07-14 · Zhiqiang Lang, Chongxing Song, Lei Zhang, Wei Wei

Binary neural network (BNN) provides a promising solution to deploy parameter-intensive deep single image super-resolution (SISR) models onto real devices with limited storage and computational resources. To achieve comp…

Image Super-ResolutionSuper-Resolution

Binarized Neural Networks on the ImageNet Classification Task

2016-04-11 · Xundong Wu, Yong Wu, Yong Zhao

We trained Binarized Neural Networks (BNNs) on the high resolution ImageNet ILSVRC-2102 dataset classification task and achieved a good performance. With a moderate size network of 13 layers, we obtained top-5 classifica…

ClassificationGeneral Classification

Binarized High-Efficiency RAW Video Restoration and Beyond

2026-08-17 · Tianyu Zhu, Ying Fu, Hesong Li, Gengchen Zhang 외 arxiv

RAW video restoration is fundamental to high-quality low-level perception and serves as the basis for a wide range of downstream vision applications. While binary neural networks (BNNs) enable efficient lightweight deplo…

Monocular Depth EstimationVideo RestorationImage EnhancementObject Detection

Efficient Conditional Diffusion Model with Probability Flow Sampling for Image Super-resolution

2024-04-16 · Yutao Yuan, Chun Yuan

Image super-resolution is a fundamentally ill-posed problem because multiple valid high-resolution images exist for one low-resolution image. Super-resolution methods based on diffusion probabilistic models can deal with…

Image Super-ResolutionSuper-Resolution