SPair-71k: A Large-scale Benchmark for Semantic Correspondence
arXiv:1908.10543
Abstract
Establishing visual correspondences under large intra-class variations, which is often referred to as semantic correspondence or semantic matching, remains a challenging problem in computer vision. Despite its significance, however, most of the datasets for semantic correspondence are limited to a small amount of image pairs with similar viewpoints and scales. In this paper, we present a new large-scale benchmark dataset of semantically paired images, SPair-71k, which contains 70,958 image pairs with diverse variations in viewpoint and scale. Compared to previous datasets, it is significantly larger in number and contains more accurate and richer annotations. We believe this dataset will provide a reliable testbed to study the problem of semantic correspondence and will help to advance research in this area. We provide the results of recent methods on our new dataset as baselines for further research. Our benchmark is available online at http://cvlab.postech.ac.kr/research/SPair-71k/.
Extension of ICCV 2019 paper, Hyperpixel Flow: Semantic Correspondence with Multi-layer Neural Features. arXiv admin note: text overlap with arXiv:1908.06537
Cited by in corpus (15)
- Hypercorrelation Squeeze for Few-Shot Segmentation
- FeatureNeRF: Learning Generalizable NeRFs by Distilling Foundation Models
- KeypointNet: A Large-scale 3D Keypoint Dataset Aggregated from Numerous Human Annotations
- CombOptNet: Fit the Right NP-Hard Problem by Learning Integer Programming Constraints
- CATs: Cost Aggregation Transformers for Visual Correspondence
- Semantic Correspondence via 2D-3D-2D Cycle
- Deep graph matching meets mixed-integer linear programming: Relax at your own risk ?
- DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence from Box Supervision
- Show, Match and Segment: Joint Weakly Supervised Learning of Semantic Matching and Object Co-segmentation
- Feature Robust Optimal Transport for High-dimensional Data
- Learning to Compose Hypercolumns for Visual Correspondence
- Convolutional Hough Matching Networks for Robust and Efficient Visual Correspondence
- Understanding Pixel-level 2D Image Semantics with 3D Keypoint Knowledge Engine
- Human Correspondence Consensus for 3D Object Semantic Understanding
- Convolutional Hough Matching Networks