IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023 · 24 citations · 49 references
ComputingComputer ScienceComputer VisionMachine VisionRobot Vision3D ReconstructionMotion EstimationMulti-view GeometryPose EstimationScene ReconstructionScene UnderstandingDeep Image FeaturesDirect AlignmentGeometric EstimationKeypoint DetectionKeypoint LocalizationSparse 3D Reconstruction
Finding local features that are repeatable across multiple views is a cornerstone of sparse 3D reconstruction. The classical image matching paradigm detects keypoints per-image once and for all, which can yield poorly-localized features and propagate large errors to the final geometry. In this article, we refine two key steps of structure-from-motion by a direct alignment of low-level image information from multiple views: we first adjust the initial keypoint locations prior to any geometric estimation, and subsequently refine points and camera poses as a post-processing. This refinement is robust to large detection noise and appearance changes, as it optimizes a featuremetric error based on dense features predicted by a neural network. This significantly improves the accuracy of camera poses and scene geometry for a wide range of keypoint detectors, challenging viewing conditions, and off-the-shelf deep features. Our system easily scales to large image collections, enabling pixel-perfect crowd-sourced localization at scale.
49
ImageNet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher et al. · 2009 IEEE Conference on Computer Vision and Pattern Recognition · 2009 · 61.8K citations
A Combined Corner and Edge Detector
Chris Harris, Matthew J. Stephens · 1988 · 12.5K citations