Diffusion models have attained remarkable breakthroughs in the real-world super-resolution (SR) task, albeit at slow inference and high demand on devices. To accelerate inference, recent works like GenDR adopt step distillation to minimize the step number to one. However, the memory boundary still restricts the maximum processing size, necessitating tile-by-tile restoration of high-resolution images. Through profiling the pipeline, we pinpoint that the variational auto-encoder (VAE) is the bottleneck of latency and memory. To completely solve the problem, we leverage pixel-(un)shuffle operations to eliminate the VAE, reversing the latent-based GenDR to pixel-space GenDR-Pix. However, upscale with x8 pixelshuffle may induce artifacts of repeated patterns. To alleviate the distortion, we propose a multi-stage adversarial distillation to progressively remove the encoder and decoder. Specifically, we utilize generative features from the previous stage models to guide adversarial discrimination. Moreover, we propose random padding to augment generative features and avoid discriminator collapse. We also introduce a masked Fourier space loss to penalize the outliers of amplitude. To improve inference performance, we empirically integrate a padding-based self-ensemble with classifier-free guidance to improve inference scaling. Experimental results show that GenDR-Pix performs 2.8x acceleration and 60% memory-saving compared to GenDR with negligible visual degradation, surpassing other one-step diffusion SR. Against all odds, GenDR-Pix can restore 4K image in only 1 second and 6GB.
LAFR: Efficient Diffusion-based Blind Face Restoration via Latent Codebook Alignment Adapter
School of Electronic and Computer Engineering, Peking University（电子与计算机工程学院，北京大学）；Computer Vision Lab, CAIDAS & IFI, University of Würzburg（计算机视觉实验室，乌尔姆大学）
Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Space
Tsinghua University（清华大学）；Carnegie Mellon University（卡内基梅隆大学）；Peking University（北京大学）；CASIA；University of Electronic Science and Technology of China（电子科技大学）；Guangming Laboratory（光明实验室）
A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse
School of Computer Science, University of St Andrews（圣安德鲁大学计算机科学学院）；Department of Data Science, City University of Hong Kong（香港城市大学数据科学系）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；School of Computer Science, University of Nottingham（诺丁汉大学计算机科学学院）；Department of Data Science and Artificial Intelligence, Monash University（墨尔本大学数据科学与人工智能系）；College of Information Science & Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）
Single-Stage Signal Attenuation Diffusion Model for Low-Light Image Enhancement and Denoising
School of Aeronautics and Astronautics, Central South University（中南大学航空航天学院）；Hunan Provincial Key Laboratory of Optic-Electronic Intelligent Measurement and Control（湖南省光电智能测控重点实验室）
Convolutional neural networks are able to learn realistic image priors from numerous training samples in low-level image generation and restoration. We show that, for high-level image recognition tasks, we can further reconstruct "realistic" images of each category by leveraging intrinsic Batch Normalization (BN) statistics without any training data. Inspired by the popular VAE/GAN methods, we regard the zero-shot optimization process of synthetic images as generative modeling to match the distribution of BN statistics. The generated images serve as a calibration set for the following zero-sho…
PMR: Physical Model-Driven Multi-Stage Restoration of Turbulent Dynamic Videos
Chengdu University of Information Technology；National Innovation Center For UHD Video Technology；School of Automation；Intelligent Sensing \& Institute of Image Processing；Pattern Recognition \& Institute of Medical Robotics, Shanghai Jiao Tong University
Sparse-to-Complete: From Sparse Image Captures to Complete 3D Scenes
State Key Lab of CAD\&CG, Zhejiang University（浙江大学CAD与CG国家重点实验室）；University of Utah（犹他大学）；Hangzhou Research Institute of Holographic and AI Technology（杭州全息与人工智能技术研究院）
Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis
The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；Huawei Noah’s Ark Lab（华为诺亚实验室）；South China University of Technology（华南理工大学）；Max Planck Institute for Informatics（马克斯·普朗克研究所（信息学））；The Hong Kong University of Science and Technology（香港科学与技术大学）
RetinaRegen: A Hybrid Model for Readability and Detail Restoration in Fundus Images
Sichuan University（四川大学）；International School,Beijing University of Posts and Telecommunications（北京邮电大学国际学院）；School of Computer Science and Technology, University of Chinese Academy of Sciences（中国科学院大学计算机科学与技术学院）
When Color-Space Decoupling Meets Diffusion for Adverse-Weather Image Restoration
School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学）；School of Electrical Engineering, Southeast University（电气工程学院，东南大学）；School of Intelligence Science and Technology, Nanjing University（智能科学与技术学院，南京大学）
Department of Electronic Engineering, University of Nigeria Nsukka（尼日利亚恩苏卡大学电子工程系）
This report describes the experimental results obtained using a proposed variational Retinex algorithm for controlled illumination correction. Two colour restoration and enhancement schemes of the algorithm are presented for drastically improved results. The algorithm modifies the reflectance image using global and local contrast enhancement approaches and gradually removes the residual illumination to yield highly pleasing results. The proposed algorithms are optimized by way of simultaneous perceptual quality metric (PQM) stabilization and entropy maximization for fully automated processing …
RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring
Shanghai Jiao Tong University（上海交通大学）；Shanghai AI Laboratory（上海人工智能实验室）；CUHK MMLab（香港中文大学多媒体实验室）；CPII under InnoHK（创新香港研究院下的CPII）；Tsinghua University（清华大学）
ExGS: Extreme 3D Gaussian Compression with Diffusion Priors
Northwestern Polytechnical University（北western工业大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；Hong Kong University of Science and Technology（香港科技大学）
