Local feature matching aims at finding correspondences between a pair of images. Although current detector-free methods leverage Transformer architecture to obtain an impressive performance, few works consider maintaining local consistency. Meanwhile, most methods struggle with large scale variations. To deal with the above issues, we propose Adaptive Spot-Guided Transformer (ASTR) for local feature matching, which jointly models the local consistency and scale variations in a unified coarse-to-fine architecture. The proposed ASTR enjoys several merits. First, we design a spot-guided aggregation module to avoid interfering with irrelevant areas during feature aggregation. Second, we design an adaptive scaling module to adjust the size of grids according to the calculated depth information at fine stage. Extensive experimental results on five standard benchmarks demonstrate that our ASTR performs favorably against state-of-the-art methods. Our code will be released on https://astr2023.github.io.
SPOT-Face: Forensic Face Identification using Attention Guided Optimal Transport
Vision Intelligence and Machine Learning (VIML) Group（视觉智能与机器学习组）；School of Computing and Electrical Engineering (SCEE)（计算与电气工程学院）；Indian Institute of Technology Mandi (IIT Mandi)（印度理工学院曼迪分校）
McGill University（麦吉尔大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）
In recent years, self-supervised denoising methods have shown impressive performance, which circumvent painstaking collection procedure of noisy-clean image pairs in supervised denoising methods and boost denoising applicability in real world. One of well-known self-supervised denoising strategies is the blind-spot training scheme. However, a few works attempt to improve blind-spot based self-denoiser in the aspect of network architecture. In this paper, we take an intuitive view of blind-spot strategy and consider its process of using neighbor pixels to predict manipulated pixels as an inpain…
How to find places that are not indexed by Google Maps? We propose an intuitive method and framework to locate places based on their distinctive spatial features. The method uses satellite and street view images in machine vision approaches to classify locations. If we can classify locations, we just need to repeat for non-overlapping locations in our area of interest. We assess the proposed system in finding Parkour spots in the campus of Arizona State University. The results are very satisfactory, having found more than 25 new Parkour spots, with a rate of true positives above 60%.
University of Oxford（牛津大学）；Baidu Research, Baidu Inc.（百度公司百度研究院）
In the stereo matching task, matching cost aggregation is crucial in both traditional methods and deep neural network models in order to accurately estimate disparities. We propose two novel neural net layers, aimed at capturing local and the whole-image cost dependencies respectively. The first is a semi-global aggregation layer which is a differentiable approximation of the semi-global matching, the second is the local guided aggregation layer which follows a traditional cost filtering strategy to refine thin structures. These two layers can be used to replace the widely used 3D convolutiona…
UBTECH Sydney AI Center, The University of Sydney（悉尼大学优必选悉尼人工智能中心）；Dalian University of Technology（大连理工大学）；Pengcheng Lab（鹏城实验室）
Occluded person re-identification is a challenging task as the appearance varies substantially with various obstacles, especially in the crowd scenario. To address this issue, we propose a Pose-guided Visible Part Matching (PVPM) method that jointly learns the discriminative features with pose-guided attention and self-mines the part visibility in an end-to-end framework. Specifically, the proposed PVPM includes two key components: 1) pose-guided attention (PGA) method for part feature pooling that exploits more discriminative local features; 2) pose-guided visibility predictor (PVP) that esti…
The University of Tokyo（东京大学）；National Institute of Advanced Industrial Science and Technology (AIST)（产业技术综合研究所）
This paper describes a viewpoint-robust object-based change detection network (OBJ-CDNet). Mobile cameras such as drive recorders capture images from different viewpoints each time due to differences in camera trajectory and shutter timing. However, previous methods for pixel-wise change detection are vulnerable to the viewpoint differences because they assume aligned image pairs as inputs. To cope with the difficulty, we introduce a deep graph matching network that establishes object correspondence between an image pair. The introduction enables us to detect object-wise scene changes without …
SPOT-Occ: Sparse Prototype-guided Transformer for Camera-based 3D Occupancy Prediction
Artificial Intelligence Thrust, The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学人工智能方向（广州））；Department of Computer Science and Engineering, The Hong Kong University of Science and Technology（香港科学与技术大学计算机科学与工程系）
Tianjin University（天津大学）；University of Warwick（华威大学）
This paper studies the task of matching image and sentence, where learning appropriate representations across the multi-modal data appears to be the main challenge. Unlike previous approaches that predominantly deploy symmetrical architecture to represent both modalities, we propose Saliency-guided Attention Network (SAN) that asymmetrically employs visual and textual attention modules to learn the fine-grained correlation intertwined between vision and language. The proposed SAN mainly includes three components: saliency detector, Saliency-weighted Visual Attention (SVA) module, and Saliency-…
We tackle the essential task of finding dense visual correspondences between a pair of images. This is a challenging problem due to various factors such as poor texture, repetitive patterns, illumination variation, and motion blur in practical scenarios. In contrast to methods that use dense correspondence ground-truths as direct supervision for local feature matching training, we train 3DG-STFM: a multi-modal matching model (Teacher) to enforce the depth consistency under 3D dense correspondence supervision and transfer the knowledge to 2D unimodal matching model (Student). Both teacher and s…
Designing face recognition systems that are capable of matching face images obtained in the thermal spectrum with those obtained in the visible spectrum is a challenging problem. In this work, we propose the use of semantic-guided generative adversarial network (SG-GAN) to automatically synthesize visible face images from their thermal counterparts. Specifically, semantic labels, extracted by a face parsing network, are used to compute a semantic loss function to regularize the adversarial network during training. These semantic cues denote high-level facial component information associated wi…
Huazhong University of Science and Technology（华中科技大学）；Alibaba Group（阿里巴巴集团）
Current few-shot action recognition methods reach impressive performance by learning discriminative features for each video via episodic training and designing various temporal alignment strategies. Nevertheless, they are limited in that (a) learning individual features without considering the entire task may lose the most relevant information in the current episode, and (b) these alignment strategies may fail in misaligned instances. To overcome the two limitations, we propose a novel Hybrid Relation guided Set Matching (HyRSM) approach that incorporates two key components: hybrid relation mo…
College of Electronics and Information Engineering, Tongji University（同济大学电子信息工程学院）；Harbin Institute of Technology Suzhou Research Institute（哈尔滨工业大学苏州研究院）；Department of Computer Science and Technology, Tongji University（同济大学计算机科学与技术系）；Multimedia Technology and Telecom Department, Telecommunications Center, Moscow Institute of Physics（莫斯科物理技术学院多媒体技术与电信系、电信中心）
Czech Technical University in Prague（布拉格捷克理工大学）；IRL 2958 GT-CNRS（法国国家科学研究中心GT联合研究实验室（IRL 2958））
We introduce Object-Guided Localization (OGuL) based on a novel method of local-feature matching. Direct matching of local features is sensitive to significant changes in illumination. In contrast, object detection often survives severe changes in lighting conditions. The proposed method first detects semantic objects and establishes correspondences of those objects between images. Object correspondences provide local coarse alignment of the images in the form of a planar homography. These homographies are consequently used to guide the matching of local features. Experiments on standard urban…
Alibaba Group（阿里巴巴集团）；Twitter（推特）；Huazhong University of Science and Technology（华中科技大学）
Recent attempts mainly focus on learning deep representations for each video individually under the episodic meta-learning regime and then performing temporal alignment to match query and support videos. However, they still suffer from two drawbacks: (i) learning individual features without considering the entire task may result in limited representation capability, and (ii) existing alignment strategies are sensitive to noises and misaligned instances. To handle the two limitations, we propose a novel Hybrid Relation guided temporal Set Matching (HyRSM++) approach for few-shot action recognit…
Restora-Flow: Mask-Guided Image Restoration with Flow Matching
Institute for Medical Informatics, Statistics and Documentation, Medical University of Graz（格拉茨医科大学医学信息学、统计学与文献研究所）；Division of Medical Physics and Biophysics, Medical University of Graz（格拉茨医科大学医学物理与生物物理部）；Institute of Visual Computing, Graz University of Technology（格拉茨技术大学视觉计算研究所）；Department of Quantitative Biomedicine, University of Zurich（苏黎世大学定量生物医学系）
RGFVR: Reference-Guided Face Video Restoration with Flow Matching
Chair of Media Technology, Munich Institute of Robotics and Machine Intelligence, School of Computation, Information, and Technology, Technical University of Munich（慕尼黑工业大学计算、信息与技术学院慕尼黑机器人与机器智能研究所媒体技术教席）
Structure-Guided Self-Supervised Matching for One-Shot Medical Landmark Detection
Department of Computer Science（计算机科学系）；Renmin University of China（中国人民大学）；University of Science and Technology of China（中国科学技术大学）；School of Biomedical Engineering（生物医学工程学院）；School of Artificial Intelligence（人工智能学院）；Shanghai Jiaotong University（上海交通大学）；Department of Orthopedics（骨科系）；Affiliated Hospital of Guizhou Medical University（贵州医科大学附属医院）；Yale University（耶鲁大学）
Why and How: Knowledge-Guided Learning for Cross-Spectral Image Patch Matching
Chinese Academy of Sciences（中国科学院）；Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；The Chinese University of Hong Kong（香港中文大学）
Joint Alignment and Distillation for Video Generation via Sample-Guided Distribution Matching
Tsinghua University（清华大学）；Kuaishou Technology（快手科技）；Harbin Institute of Technology (ShenZhen)（哈尔滨工业大学（深圳））；Beijing University of Posts and Telecommunications（北京邮电大学）
We present Hierarchical Memory Matching Network (HMMN) for semi-supervised video object segmentation. Based on a recent memory-based method [33], we propose two advanced memory read modules that enable us to perform memory reading in multiple scales while exploiting temporal smoothness. We first propose a kernel guided memory matching module that replaces the non-local dense memory read, commonly adopted in previous memory-based methods. The module imposes the temporal smoothness constraint in the memory read, leading to accurate memory retrieval. More importantly, we introduce a hierarchical …
One key challenge of exemplar-guided image generation lies in establishing fine-grained correspondences between input and guided images. Prior approaches, despite the promising results, have relied on either estimating dense attention to compute per-point matching, which is limited to only coarse scales due to the quadratic memory cost, or fixing the number of correspondences to achieve linear complexity, which lacks flexibility. In this paper, we propose a dynamic sparse attention based Transformer model, termed Dynamic Sparse Transformer (DynaST), to achieve fine-level matching with favorabl…
Technical University of Munich（慕尼黑工业大学）；CIIRC Czech Technical University in Prague（布拉格捷克技术大学CIIRC）
The classical matching pipeline used for visual localization typically involves three steps: (i) local feature detection and description, (ii) feature matching, and (iii) outlier rejection. Recently emerged correspondence networks propose to perform those steps inside a single network but suffer from low matching resolution due to the memory bottleneck. In this work, we propose a new perspective to estimate correspondences in a detect-to-refine manner, where we first predict patch-level match proposals and then refine them. We present Patch2Pix, a novel refinement network that refines match pr…
The complementary fusion of light detection and ranging (LiDAR) data and image data is a promising but challenging task for generating high-precision and high-density point clouds. This study proposes an innovative LiDAR-guided stereo matching approach called LiDAR-guided stereo matching (LGSM), which considers the spatial consistency represented by continuous disparity or depth changes in the homogeneous region of an image. The LGSM first detects the homogeneous pixels of each LiDAR projection point based on their color or intensity similarity. Next, we propose a riverbed enhancement function…
Match4Annotate: Cross-Video Annotation Transfer in Ultrasound via Implicit Feature Flow-Guided Matching
Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, USA（麻省理工学院机械工程系）；Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge, USA（麻省理工学院医学工程与科学研究所）；MIT.nano Immersion Lab, Massachusetts Institute of Technology, Cambridge, USA（麻省理工学院MIT.nano沉浸实验室）
Resolving the Ambiguity of Complete-to-Partial Point Cloud Registration for Image-Guided Liver Surgery with Patches-to-Partial Matching
Center for Imaging Science and Department of Biomedical Engineering, Rochester Institute of Technology（成像科学中心和生物医学工程系，罗切斯特理工学院）；Department of Biomedical Engineering, Vanderbilt University（生物医学工程系，范德比尔特大学）；School of Science and Engineering, University of Missouri – Kansas City（科学与工程学院，密苏里大学-堪萨斯城分校）
Occluded person re-identification is a challenging task as human body parts could be occluded by some obstacles (e.g. trees, cars, and pedestrians) in certain scenes. Some existing pose-guided methods solve this problem by aligning body parts according to graph matching, but these graph-based methods are not intuitive and complicated. Therefore, we propose a transformer-based Pose-guided Feature Disentangling (PFD) method by utilizing pose information to clearly disentangle semantic components (e.g. human body or joint parts) and selectively match non-occluded parts correspondingly. First, Vis…
Frequency Prior Guided Matching: A Data Augmentation Approach for Generalizable Semi-Supervised Polyp Segmentation
Academy of Medical Engineering and Translational Medicine, Tianjin University（天津大学医学工程与转化医学研究院）；Hangzhou Institute of Medicine, Chinese Academy of Sciences（杭州医学研究所）；Yale University（耶鲁大学）
3D-Guided Scalable Flow Matching for Generating Volumetric Tissue Spatial Transcriptomics from Serial Histology
Cambridge Stem Cell Institute, University of Cambridge（剑桥干细胞研究所，剑桥大学）；Cambridge Center for AI in Medicine, University of Cambridge（剑桥人工智能医学中心，剑桥大学）；Department of Medicine, University of Cambridge（剑桥大学医学系）；Computer Science Department, University of Oxford（牛津大学计算机科学系）；Computer Science Department, University of Helsinki（赫尔辛基大学计算机科学系）；Institute for Molecular Medicine Finland, University of Helsinki（芬兰分子医学研究所，赫尔辛基大学）；Wellcome Sanger Institute（沃森桑格研究所）
Beyond Image-Text Matching: Verb Understanding in Multimodal Transformers Using Guided Masking
Faculty of Information Technology, Brno University of Technology（布尔诺理工大学信息技术学院）；Kempelen Institute of Intelligent Technologies（肯佩伦智能技术研究所）；George Mason University（乔治梅森大学）
GuideFlow: Constraint-Guided Flow Matching for Planning in End-to-End Autonomous Driving
School of Computer Science and Technology, Beijing Jiaotong University（北京交通大学计算机科学与技术学院）；Beijing Key Laboratory of Traffic Data Mining and Embodied Intelligence（北京交通大数据挖掘与具身智能重点实验室）；Qcraft；Yanshan University（燕山大学）；Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；The University of Queensland（昆士兰大学）
Feature distillation is an effective way to improve the performance for a smaller student model, which has fewer parameters and lower computation cost compared to the larger teacher model. Unfortunately, there is a common obstacle - the gap in semantic feature structure between the intermediate features of teacher and student. The classic scheme prefers to transform intermediate features by adding the adaptation module, such as naive convolutional, attention-based or more complicated one. However, this introduces two problems: a) The adaptation module brings more parameters into training. b) T…
Stereo is a prominent technique to infer dense depth maps from images, and deep learning further pushed forward the state-of-the-art, making end-to-end architectures unrivaled when enough data is available for training. However, deep networks suffer from significant drops in accuracy when dealing with new environments. Therefore, in this paper, we introduce Guided Stereo Matching, a novel paradigm leveraging a small amount of sparse, yet reliable depth measurements retrieved from an external source enabling to ameliorate this weakness. The additional sparse cues required by our method can be o…
Towards Natural Language-Guided Drones: GeoText-1652 Benchmark with Spatial Relation Matching
School of Computing, National University of Singapore（新加坡国立大学计算机学院）；FST and ICI, University of Macau（澳门大学科技学院与当代计算机与软件研究所）；School of Communication Engineering, Hangzhou Dianzi University（杭州电子科技大学通信工程学院）
