Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision最新文献

Architecture-Agnostic Untrained Network Priors for Image Reconstruction with Frequency Regularization. 基于频率正则化的图像重构非训练网络先验算法。

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2025-01-01 Epub Date: 2024-12-05 DOI: 10.1007/978-3-031-72630-9_20

Yilin Liu, Yunkui Pang, Jiang Li, Yong Chen, Pew-Thian Yap

{"title":"Architecture-Agnostic Untrained Network Priors for Image Reconstruction with Frequency Regularization.","authors":"Yilin Liu, Yunkui Pang, Jiang Li, Yong Chen, Pew-Thian Yap","doi":"10.1007/978-3-031-72630-9_20","DOIUrl":"10.1007/978-3-031-72630-9_20","url":null,"abstract":"Untrained networks inspired by deep image priors have shown promising capabilities in recovering high-quality images from noisy or partial measurements without requiring training sets. Their success is widely attributed to implicit regularization due to the spectral bias of suitable network architectures. However, the application of such network-based priors often entails superfluous architectural decisions, risks of overfitting, and lengthy optimization processes, all of which hinder their practicality. To address these challenges, we propose efficient architecture-agnostic techniques to directly modulate the spectral bias of network priors: 1) bandwidth-constrained input, 2) bandwidth-controllable upsamplers, and 3) Lipschitz-regularized convolutional layers. We show that, with just a few lines of code, we can reduce overfitting in underperforming architectures and close performance gaps with high-performing counterparts, minimizing the need for extensive architecture tuning. This makes it possible to employ a more compact model to achieve performance similar or superior to larger models while reducing runtime. Demonstrated on inpainting-like MRI reconstruction task, our results signify for the first time that architectural biases, overfitting, and runtime issues of untrained network priors can be simultaneously addressed without architectural modifications. Our code is publicly available .","PeriodicalId":72676,"journal":{"name":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","volume":"15072 ","pages":"341-358"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11670387/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142904254","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Zero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems. 反问题中扩散模型近似后验抽样的零弹自适应。

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2025-01-01 Epub Date: 2024-11-10 DOI: 10.1007/978-3-031-73010-8_26

Yaşar Utku Alçalar, Mehmet Akçakaya

{"title":"Zero-Shot Adaptation for Approximate Posterior Sampling of Diffusion Models in Inverse Problems.","authors":"Yaşar Utku Alçalar, Mehmet Akçakaya","doi":"10.1007/978-3-031-73010-8_26","DOIUrl":"https://doi.org/10.1007/978-3-031-73010-8_26","url":null,"abstract":"Diffusion models have emerged as powerful generative techniques for solving inverse problems. Despite their success in a variety of inverse problems in imaging, these models require many steps to converge, leading to slow inference time. Recently, there has been a trend in diffusion models for employing sophisticated noise schedules that involve more frequent iterations of timesteps at lower noise levels, thereby improving image generation and convergence speed. However, application of these ideas for solving inverse problems with diffusion models remain challenging, as these noise schedules do not perform well when using empirical tuning for the forward model log-likelihood term weights. To tackle these challenges, we propose zero-shot approximate posterior sampling (ZAPS) that leverages connections to zero-shot physics-driven deep learning. ZAPS fixes the number of sampling steps, and uses zero-shot training with a physics-guided loss function to learn log-likelihood weights at each irregular timestep. We apply ZAPS to the recently proposed diffusion posterior sampling method as baseline, though ZAPS can also be used with other posterior sampling diffusion models. We further approximate the Hessian of the logarithm of the prior using a diagonalization approach with learnable diagonal entries for computational efficiency. These parameters are optimized over a fixed number of epochs with a given computational budget. Our results for various noisy inverse problems, including Gaussian and motion deblurring, inpainting, and super-resolution show that ZAPS reduces inference time, provides robustness to irregular noise schedules and improves reconstruction quality. Code is available at https://github.com/ualcalar17/ZAPS.","PeriodicalId":72676,"journal":{"name":"Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision","volume":"15141 ","pages":"444-460"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11736016/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143017349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval 面向无监督视频检索的双流知识保持哈希算法

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2023-10-12 DOI: 10.1007/978-3-031-19781-9_11

P. Li, Hongtao Xie, Jiannan Ge, Lei Zhang, Shaobo Min, Yongdong Zhang

引用次数: 9

Spatial and Visual Perspective-Taking via View Rotation and Relation Reasoning for Embodied Reference Understanding 通过视角旋转和关系推理的空间和视觉视角获取对具体化参考理解的影响

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2023-09-03 DOI: 10.1007/978-3-031-20059-5_12

Cheng Shi, Sibei Yang

引用次数: 5

Rethinking Confidence Calibration for Failure Prediction 失效预测置信度校准的再思考

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2023-03-06 DOI: 10.1007/978-3-031-19806-9_30

Fei Zhu, Zhen Cheng, Xu-Yao Zhang, Cheng-Lin Liu

引用次数: 11

PCR-CG: Point Cloud Registration via Deep Explicit Color and Geometry PCR-CG:点云配准通过深显色和几何

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2023-02-28 DOI: 10.1007/978-3-031-20080-9_26

Yu Zhang, Junle Yu, Xiaolin Huang, Wenhui Zhou, Ji Hou

引用次数: 7

Diverse Human Motion Prediction Guided by Multi-level Spatial-Temporal Anchors 基于多层次时空锚点的多种人体运动预测

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2023-02-09 DOI: 10.1007/978-3-031-20047-2_15

Sirui Xu, Yu-Xiong Wang, Liangyan Gui

引用次数: 15

Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detection 桥接图像和视频:一个用于大词汇视频对象检测的简单学习框架

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-12-20 DOI: 10.1007/978-3-031-19806-9_14

Sanghyun Woo, KwanYong Park, Seoung Wug Oh, In-So Kweon, Joon-Young Lee

引用次数: 3

Union-Set Multi-source Model Adaptation for Semantic Segmentation 基于联合集的多源模型自适应语义分割

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-12-06 DOI: 10.1007/978-3-031-19818-2_33

Zongyao Li, Ren Togo, Takahiro Ogawa, M. Haseyama

引用次数: 2

Interclass Prototype Relation for Few-Shot Segmentation 基于类间原型关系的少镜头分割

Computer vision - ECCV ... : ... European Conference on Computer Vision : proceedings. European Conference on Computer Vision Pub Date : 2022-11-16 DOI: 10.1007/978-3-031-19818-2_21

A. Okazawa

引用次数: 9