Wide-baseline matching focussing on problems with extreme viewpoint change is considered. We introduce the use of view synthesis with affine-covariant detectors to solve such problems and show that matching with the Hessian-Affine or MSER detectors outperforms the state-of-the-art ASIFT.
To minimise the loss of speed caused by view synthesis, we propose the Matching On Demand with view Synthesis algorithm (MODS) that uses progressively more synthesized images and more (time-consuming) detectors until reliable estimation of geometry is possible. We show experimentally that the MODS algorithm solves problems beyond the state-of-the-art and yet is comparable in speed to standard wide-baseline matchers on simpler problems.
Minor contributions include an improved method for tentative correspondence selection, applicable both with and without view synthesis and a view synthesis setup greatly improving MSER robustness to blur and scale change that increase its running time by 10% only.
DeepShapeMatchingKit: Accelerated Functional Map Solver and Shape Matching Pipelines Revisited
Technical University of Munich（慕尼黑工业大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；MIT（麻省理工学院）；Adobe；Imperial College London（帝国理工学院）；Simon Fraser University（西蒙菲莎大学）
Chalmers University of Technology（查尔姆斯理工大学）；Linköping University（林雪平大学）；University of Amsterdam（阿姆斯特丹大学）；Centre for Mathematical Sciences, Lund University（隆德大学数学科学中心）
GeodesicNVS: Probability Density Geodesic Flow Matching for Novel View Synthesis
Huawei Hilbert Research Center (Dresden)（华为希尔伯特研究中心（德累斯顿））；Technical University of Munich（慕尼黑工业大学）；Karlsruhe University of Applied Sciences（卡尔斯鲁厄应用科学大学）
CrackSegFlow: Controllable Flow Matching Synthesis for Generalizable Crack Segmentation with a 50K Image-Mask Benchmark
Department of Civil and Environmental Engineering, Grainger College of Engineering, University of Illinois Urbana--Champaign（土木与环境工程系，格拉inger工程学院，伊利诺伊大学厄巴纳-香槟分校）；Department of Computer Science, Grainger College of Engineering, University of Illinois Urbana--Champaign（计算机科学系，格拉inger工程学院，伊利诺伊大学厄巴纳-香槟分校）
WFM: 3D Wavelet Flow Matching for Ultrafast Multi-Modal MRI Synthesis
Department of Computer Science, Stanford University（斯坦福大学计算机科学系）；Machine and Hybrid Intelligence Lab, Feinberg School of Medicine, Northwestern University（北western大学费因伯格医学院机器与混合智能实验室）
本文提出WFM方法，通过学习基于小波空间条件均值的直接流，实现高效多模态MRI合成，单模型在BraTS 2024上达到26.8 dB PSNR和0.94 SSIM，速度比扩散模型快250-1000倍。
College of Artificial Intelligence and Automation, Hohai University（人工智能与自动化学院，河海大学）；College of DaYu, Hohai University（大禹学院，河海大学）；College of Water Conserwancy and Hydropower Engineering, Hohai University（水利水电工程学院，河海大学）；College of Computer Science and Technology, Zhejiang University of Technology（计算机科学与技术学院，浙江工业大学）
Adversarial Distribution Matching for Diffusion Distillation Towards Efficient Image and Video Synthesis
Sun Yat-Sen University（中山大学）；ByteDance Seed Vision（字节跳动种子视觉）；Guangdong Provincial Key Laboratory of Information Security Technology（广东省信息安全技术重点实验室）；Key Laboratory of Machine Intelligence and Advanced Computing, Ministry of Education, China（教育部机器智能与高级计算重点实验室）；Pazhou Lab (HuangPu), Guangzhou, China（琶洲实验室（黄埔），广州，中国）
Few-Shot Distribution-Aligned Flow Matching for Data Synthesis in Medical Image Segmentation
Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education, School of Cyber Science and Engineering, Wuhan University（武汉大学网络空间安全学院、空天信息安全与可信计算教育部重点实验室）；Shanghai Innovation Institute（上海创新研究院）；Shanghai AI Laboratory（上海人工智能实验室）
Rover Relocalization for Mars Sample Return by Virtual Template Synthesis and Matching
McGill University（麦吉尔大学）；Facebook AI Research（脸书人工智能研究实验室）；University of Michigan（密歇根大学）；Carnegie Mellon University（卡内基梅隆大学）；Jet Propulsion Laboratory（喷气推进实验室）；California Institute of Technology（加州理工学院）
我们认为，在名义上的火星样品返回运动的背景下，漫游车重新定位的问题。在这一活动中，漫游车（R1）需要能够使用另一个漫游车（R0）多年前收集的参考图像在大约50 x 50 m的区域内自主导航和定位。我们提出了一个视觉定位器，表现出鲁棒性相对贫瘠的地形，我们希望在相关领域找到，以及大的照明和R0和R1之间的视点差异。定位器合成从参考R0图像构建的网格的部分渲染，并将其与R1图像进行匹配。我们在总共2160张图像的数据集上评估了我们的方法，这些图像涵盖了预期环境条件（地形、照明、接近角）的范围。实验结果表明了该方法的有效性。这项工作为火星样品返回活动提供了信息，该活动将选择一个地点，在那里毅力号（R0）将放置一组样品管，以便将来由另一个漫游者（R1）取回。
Learning Energy-Based Models in High-Dimensional Spaces with Multi-scale Denoising Score Matching
Redwood Center for Theoretical Neuroscience（雷德伍德理论神经科学中心）；University of California Berkeley（加州大学伯克利分校）；Berkeley AI Research（伯克利人工智能研究院）；Helen Wills Neuroscience Institute（海伦·威尔斯神经科学研究所）
