Dense Matchers for Dense Tracking
Not on the map. Why?
Abstract (arXiv)
Optical flow is a useful input for various applications, including 3D reconstruction, pose estimation, tracking, and structure-from-motion. Despite its utility, the field of dense long-term tracking, especially over wide baselines, has not been extensively explored. This paper extends the concept of combining multiple optical flows over logarithmically spaced intervals as proposed by MFT. We demonstrate the compatibility of MFT with different optical flow networks, yielding results that surpass their individual performance. Moreover, we present a simple yet effective combination of these networks within the MFT framework. This approach proves to be competitive with more sophisticated, non-causal methods in terms of position prediction accuracy, highlighting the potential of MFT in enhancing long-term tracking applications.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 33 of its 59 references that are in the map. First posted on arXiv 17 Feb 2024.
Builds on
33 of 59 references.
References · 33
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
- 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,385
- 2015FlowNet: Learning Optical Flow with Convolutional Networkscited by 1,054
- 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
- 2016FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networkscited by 780
- 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 731
- 2023Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesiscited by 731
- 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
21 more
- 2023CoTracker: It is Better to Track Togethercited by 516
- 2018ATOM: Accurate Tracking by Overlap Maximizationcited by 285
- 2023TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinementcited by 281
- 2022FlowFormer: A Transformer Architecture for Optical Flowcited by 273
- 2022TAP-Vid: A Benchmark for Tracking Any Point in a Videocited by 258
- 2021Learning to Estimate Hidden Motions with Global Motion Aggregationcited by 223
- 2022Particle Video Revisited: Tracking Through Occlusions Using Point Trajectoriescited by 215
- 2023Tracking Everything Everywhere All at Oncecited by 190
- 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
- 2022DKM: Dense Kernelized Feature Matching for Geometry Estimationcited by 174
- 2023BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objectscited by 144
- 2019GLU-Net: Global-Local Universal Network for Dense Flow and Correspondencescited by 139
- 2019Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimationcited by 131
- 2021LASR: Learning Articulated Shape Reconstruction from a Monocular Videocited by 115
- 2018Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimationcited by 69
- 2019D3S -- A Discriminative Single Shot Segmentation Trackercited by 69
- 2021DOVE: Learning Deformable 3D Objects by Watching Videoscited by 61
- 2023MFT: Long-Term Tracking of Every Pixelcited by 61
- 2020RANSAC-Flow: generic two-stage image alignmentcited by 48
- 2022DirectTracker: 3D Multi-Object Tracking Using Direct Image Alignment and Photometric Bundle Adjustmentcited by 6
- 2023Tracking by 3D Model Estimation of Unknown Objects in Videoscited by 5
Built on by
Citing papers per year: 2024: 1.
1 paper.