# LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

arXiv: https://arxiv.org/abs/2401.01887 · HTML: https://mlsanity.com/paper/2401.01887/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 56 references that are in the map.
- First posted on arXiv 3 Jan 2024.

## Builds on (most cited first, 30 of 39)

- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [ORB-SLAM: a Versatile and Accurate Monocular SLAM System](https://mlsanity.com/paper/1502.00956/) (2015)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Unsupervised Learning of Depth and Ego-Motion from Video](https://mlsanity.com/paper/1704.07813/) (2017)
- [DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras](https://mlsanity.com/paper/2108.10869/) (2021)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [TartanAir: A Dataset to Push the Limits of Visual SLAM](https://mlsanity.com/paper/2003.14338/) (2020)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [In-Place Scene Labelling and Understanding with Implicit Scene Representation](https://mlsanity.com/paper/2103.15875/) (2021)
- [GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose](https://mlsanity.com/paper/1803.02276/) (2018)
- [TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement](https://mlsanity.com/paper/2306.08637/) (2023)
- [PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking](https://mlsanity.com/paper/2307.15055/) (2023)
- [TAP-Vid: A Benchmark for Tracking Any Point in a Video](https://mlsanity.com/paper/2211.03726/) (2022)
- [Space-Time Correspondence as a Contrastive Random Walk](https://mlsanity.com/paper/2006.14613/) (2020)
- [Competitive Collaboration: Joint Unsupervised Learning of Depth, Camera Motion, Optical Flow and Motion Segmentation](https://mlsanity.com/paper/1805.09806/) (2018)
- [Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories](https://mlsanity.com/paper/2204.04153/) (2022)
- [EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision](https://mlsanity.com/paper/2311.02077/) (2023)
- [D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry](https://mlsanity.com/paper/2003.01060/) (2020)
- [Tracking Everything Everywhere All at Once](https://mlsanity.com/paper/2306.05422/) (2023)
- [Deep Patch Visual Odometry](https://mlsanity.com/paper/2208.04726/) (2022)
- [Robust Consistent Video Depth Estimation](https://mlsanity.com/paper/2012.05901/) (2020)
- [DeepV2D: Video to Depth with Differentiable Structure from Motion](https://mlsanity.com/paper/1812.04605/) (2018)
- [DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networks](https://mlsanity.com/paper/1709.08429/) (2017)
- [Video Object Segmentation with Language Referring Expressions](https://mlsanity.com/paper/1803.08006/) (2018)
- [CodeSLAM - Learning a Compact, Optimisable Representation for Dense Visual SLAM](https://mlsanity.com/paper/1804.00874/) (2018)
- [D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video](https://mlsanity.com/paper/2205.15838/) (2022)
- [DynaSLAM: Tracking, Mapping and Inpainting in Dynamic Scenes](https://mlsanity.com/paper/1806.05620/) (2018)
- [Self-supervised Learning with Geometric Constraints in Monocular Video: Connecting Flow, Depth, and Camera](https://mlsanity.com/paper/1907.05820/) (2019)

## Built on by (most cited first, 30 of 56)

- [Continuous 3D Perception Model with Persistent State](https://mlsanity.com/paper/2501.12387/) (2025)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos](https://mlsanity.com/paper/2412.04463/) (2024)
- [MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds](https://mlsanity.com/paper/2405.17421/) (2024)
- [BootsTAP: Bootstrapped Training for Tracking-Any-Point](https://mlsanity.com/paper/2402.00847/) (2024)
- [Align3R: Aligned Monocular Depth Estimation for Dynamic Videos](https://mlsanity.com/paper/2412.03079/) (2024)
- [DELTA: Dense Efficient Long-range 3D Tracking for any video](https://mlsanity.com/paper/2410.24211/) (2024)
- [CamCloneMaster: Enabling Reference-based Camera Control for Video Generation](https://mlsanity.com/paper/2506.03140/) (2025)
- [LONG3R: Long Sequence Streaming 3D Reconstruction](https://mlsanity.com/paper/2507.18255/) (2025)
- [Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video](https://mlsanity.com/paper/2503.21761/) (2025)
- [Dynamic Camera Poses and Where to Find Them](https://mlsanity.com/paper/2504.17788/) (2025)
- [Back on Track: Bundle Adjustment for Dynamic Scene Reconstruction](https://mlsanity.com/paper/2504.14516/) (2025)
- [RoMo: Robust Motion Segmentation Improves Structure from Motion](https://mlsanity.com/paper/2411.18650/) (2024)
- [AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos](https://mlsanity.com/paper/2503.23282/) (2025)
- [Can Visual Foundation Models Achieve Long-term Point Tracking?](https://mlsanity.com/paper/2408.13575/) (2024)
- [Benchmarking Egocentric Visual-Inertial SLAM at City Scale](https://mlsanity.com/paper/2509.26639/) (2025)
- [Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels](https://mlsanity.com/paper/2603.02573/) (2026)
- [Can Video Diffusion Model Reconstruct 4D Geometry?](https://mlsanity.com/paper/2503.21082/) (2025)
- [4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation](https://mlsanity.com/paper/2511.18416/) (2025)
- [ETAP: Event-based Tracking of Any Point](https://mlsanity.com/paper/2412.00133/) (2024)
- [Flow3r: Factored Flow Prediction for Scalable Visual Geometry Learning](https://mlsanity.com/paper/2602.20157/) (2026)
- [Scene-agnostic Pose Regression for Visual Localization](https://mlsanity.com/paper/2503.19543/) (2025)
- [C4D: 4D Made from 3D through Dual Correspondences](https://mlsanity.com/paper/2510.14960/) (2025)
- [TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels](https://mlsanity.com/paper/2512.08358/) (2025)
- [HumanMM: Global Human Motion Recovery from Multi-shot Videos](https://mlsanity.com/paper/2503.07597/) (2025)
- [DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling](https://mlsanity.com/paper/2512.03000/) (2025)
- [MATE: Motion-Augmented Temporal Consistency for Event-based Point Tracking](https://mlsanity.com/paper/2412.01300/) (2024)
- [Online Dense Point Tracking with Streaming Memory](https://mlsanity.com/paper/2503.06471/) (2025)
- [Princeton365: A Diverse Dataset with Accurate Camera Pose](https://mlsanity.com/paper/2506.09035/) (2025)
- [AnthroTAP: Learning Point Tracking with Real-World Motion](https://mlsanity.com/paper/2507.06233/) (2025)

## Abstract (arXiv)

Visual odometry estimates the motion of a moving camera based on visual input. Existing methods, mostly focusing on two-view point tracking, often ignore the rich temporal context in the image sequence, thereby overlooking the global motion patterns and providing no assessment of the full trajectory reliability. These shortcomings hinder performance in scenarios with occlusion, dynamic objects, and low-texture areas. To address these challenges, we present the Long-term Effective Any Point Tracking (LEAP) module. LEAP innovatively combines visual, inter-track, and temporal cues with mindfully selected anchors for dynamic track estimation. Moreover, LEAP's temporal probabilistic formulation integrates distribution updates into a learnable iterative refinement module to reason about point-wise uncertainty. Based on these traits, we develop LEAP-VO, a robust visual odometry system adept at handling occlusions and dynamic scenes. Our mindful integration showcases a novel practice by employing long-term point tracking as the front-end. Extensive experiments demonstrate that the proposed pipeline significantly outperforms existing baselines across various visual odometry benchmarks.