We propose a novel framework for finding correspondences in images based on a deep neural network that, given two images and a query point in one of them, finds its correspondence in the other.
Ranked #1 on Dense Pixel Correspondence Estimation on ETH3D
Local feature frameworks are difficult to learn in an end-to-end fashion, due to the discreteness inherent to the selection and matching of sparse keypoints.
Ranked #3 on Image Matching on IMC PhotoTourism (using extra training data)
We introduce a comprehensive benchmark for local features and robust estimation algorithms, focusing on the downstream task -- the accuracy of the reconstructed camera pose -- as our primary metric.
Many problems in computer vision require dealing with sparse, unordered data in the form of point clouds.
We propose a novel image sampling method for differentiable image transformation in deep neural networks.
We present a novel deep architecture and a training strategy to learn a local feature pipeline from scratch, using collections of images without the need for human supervision.
We demonstrate that our models outperform the state-of-the-art on ultra-wide baseline matching and approach human accuracy.
We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description.
Deep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, such as correspondence, still rely on hand-crafted features, e. g. SIFT.
Ranked #2 on Satellite Image Classification on SAT-4
In this work we propose a technique to combine bottom-up segmentation, coming in the form of SLIC superpixels, with sliding window detectors, such as Deformable Part Models (DPMs).
In this work we exploit segmentation to construct appearance descriptors that can robustly deal with occlusion and background changes.