A Large Dataset For Improving Patch Matching

Abstract

We propose a new dataset for learning local image descriptors which can be used for significantly improved patch matching. Our proposed dataset consists of an order of magnitude more number of scenes, images, and positive and negative correspondences compared to the currently available Multi-View Stereo (MVS) dataset from Brown et al. The new dataset also has better coverage of the overall viewpoint, scale, and lighting changes in comparison to the MVS dataset. Our dataset also provides supplementary information like RGB patches with scale and rotations values, and intrinsic and extrinsic camera parameters which as shown later can be used to customize training data as per application. We train an existing state-of-the-art model on our dataset and evaluate on publicly available benchmarks such as HPatches dataset and Strecha et al.\cite\{strecha\} to quantify the image descriptor performance. Experimental evaluations show that the descriptors trained using our proposed dataset outperfor

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymitra2018a

Related papers

• Hpatches: A Benchmark And Evaluation Of Handcrafted And Learned Local Descriptors (2017)11.08
• Pn-net: Conjoined Triple Deep Network For Learning Local Image Descriptors (2016)0.00
• Patch-wise Retrieval: A Bag Of Practical Techniques For Instance-level Matching (2025)0.00
• LCD: Learned Cross-domain Descriptors For 2D-3D Matching (2019)13.74
• Convolutional Patch Representations For Image Retrieval: An Unsupervised Approach (2016)12.47
• Learning Local Descriptors By Optimizing The Keypoint-correspondence Criterion: Applications To Face Matching, Learning From Unlabeled Videos And 3d-shape Retrieval (2016)11.75
• Working Hard To Know Your Neighbor's Margins: Local Descriptor Learning Loss (2017)0.00
• End-to-end Learning Of Keypoint Detector And Descriptor For Pose Invariant 3D Matching (2018)12.40