mlsanityData to 7 Oct 2026

Deep Patch Visual SLAM

arXiv 2408.01654 ↗First posted 3 Aug 2024cs.CVcited by 68

Not on the map. Why?

Abstract (arXiv)

Recent work in visual SLAM has shown the effectiveness of using deep network backbones. Despite excellent accuracy, however, such approaches are often expensive to run or do not generalize well zero-shot. Their runtime can also fluctuate wildly while their frontend and backend fight for access to GPU resources. To address these problems, we introduce Deep Patch Visual (DPV) SLAM, a method for monocular visual SLAM on a single GPU. DPV-SLAM maintains a high minimum framerate and small memory overhead (5-7G) compared to existing deep SLAM systems. On real-world datasets, DPV-SLAM runs at 1x-4x real-time framerates. We achieve comparable accuracy to DROID-SLAM on EuRoC and TartanAir while running 2.5x faster using a fraction of the memory. DPV-SLAM is an extension to the DPVO visual odometry system; its code can be found in the same repository: https://github.com/princeton-vl/DPVO

Key facts. Cited by 68 papers in the map (data through 7 Oct 2026). Builds on 41 of its 53 references that are in the map. First posted on arXiv 3 Aug 2024.

Builds on

41 of 53 references.

References · 41

  1. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  2. 2015ORB-SLAM: a Versatile and Accurate Monocular SLAM Systemcited by 983
  3. 2019The Replica Dataset: A Digital Replica of Indoor Spacescited by 885
  4. 2020ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAMcited by 862
  5. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  6. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  7. 2021NICE-SLAM: Neural Implicit Scalable Encoding for SLAMcited by 586
  8. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  9. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  10. 2016Direct Sparse Odometrycited by 479
  11. 2021iMAP: Implicit Mapping and Positioning in Real-Timecited by 476
  12. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 386
29 more
  1. 2023Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Imagecited by 357
  2. 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
  3. 2020DISK: Learning local features with policy gradientcited by 310
  4. 2019Kornia: an Open Source Differentiable Computer Vision Library for PyTorchcited by 231
  5. 2020D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometrycited by 206
  6. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 200
  7. 2022NeRF-SLAM: Real-Time Dense Monocular SLAM with Neural Radiance Fieldscited by 188
  8. 2022Deep Patch Visual Odometrycited by 186
  9. 2018DeepV2D: Video to Depth with Differentiable Structure from Motioncited by 185
  10. 2017DeepVO: Towards End-to-End Visual Odometry with Deep Recurrent Convolutional Neural Networkscited by 173
  11. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 140
  12. 2023GO-SLAM: Global Optimization for Consistent 3D Instant Reconstructioncited by 132
  13. 2020DeepFactors: Real-Time Probabilistic Dense Monocular SLAMcited by 117
  14. 2020TartanVO: A Generalizable Learning-based VOcited by 107
  15. 2017UnDeepVO: Monocular Visual Odometry through Unsupervised Deep Learningcited by 95
  16. 2018DeepTAM: Deep Tracking and Mappingcited by 87
  17. 20204Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Drivingcited by 51
  18. 2018LDSO: Direct Sparse Odometry with Loop Closurecited by 50
  19. 2023Dense RGB SLAM with Neural Implicit Mapscited by 42
  20. 2020VDO-SLAM: A Visual Dynamic Object-aware SLAM Systemcited by 39
  21. 2016A Photometrically Calibrated Benchmark For Monocular Visual Odometrycited by 32
  22. 2024WHAC: World-grounded Humans and Camerascited by 29
  23. 2022DytanVO: Joint Refinement of Visual Odometry and Motion Segmentation in Dynamic Environmentscited by 27
  24. 2022PVO: Panoptic Visual Odometrycited by 26
  25. 2017maplab: An Open Framework for Research in Visual-inertial Mapping and Localizationcited by 23
  26. 2021DF-VO: What Should Be Learnt for Visual Odometry?cited by 22
  27. 2023Monocular Visual-Inertial Depth Estimationcited by 18
  28. 2023iSLAM: Imperative SLAMcited by 14
  29. 2022D3FlowSLAM: Self-Supervised Dynamic SLAM with Flow Motion Decomposition and DINO Guidancecited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 24; 2026: 37.

68 papers.

Sort:

By area:

  1. 2024MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priorscited by 198
  2. 2025VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifoldcited by 130
  3. 2025VGGT-Long: Chunk it, Loop it, Align it -- Pushing VGGT's Limits on Kilometer-scale Long RGB Sequencescited by 107
  4. 2025TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigationcited by 35
  5. 2026LoGeR: Long-Context Geometric Reconstruction with Hybrid Memorycited by 33
  6. 2026Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstructioncited by 25
  7. 2024HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstructioncited by 24
  8. 2026VGGT-SLAM 2.0: Real-time Dense Feed-forward Scene Reconstructioncited by 22
  9. 2025SAIL-Recon: Large SfM by Augmenting Scene Regression with Localizationcited by 18
  10. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 16
  11. 2024DROID-Splat: Combining end-to-end SLAM with 3D Gaussian Splattingcited by 15
  12. 2025GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splatscited by 14
38 more
  1. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 13
  2. 2025ViSTA-SLAM: Visual SLAM with Symmetric Two-view Associationcited by 13
  3. 2025Benchmarking Egocentric Visual-Inertial SLAM at City Scalecited by 12
  4. 2024FIction: 4D Future Interaction Prediction from Videocited by 8
  5. 2025SLAM-Former: Putting SLAM into One Transformercited by 7
  6. 2025ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representationcited by 6
  7. 2024MambaVO: Deep Visual Odometry Based on Sequential Matching Refinement and Training Smoothingcited by 5
  8. 2025DINO-VO: A Feature-based Visual Odometry Leveraging a Visual Foundation Modelcited by 5
  9. 2025LASER: Layer-wise Scale Alignment for Training-Free Streaming 4D Reconstructioncited by 5
  10. 2026Video Understanding: From Geometry and Semantics to Unified Modelscited by 5
  11. 2024ROVER: A Multi-Season Dataset for Visual SLAMcited by 4
  12. 2025VSLAM-LAB: A Comprehensive Framework for Visual SLAM Methods and Datasetscited by 4
  13. 2025ZeroVO: Visual Odometry with Minimal Assumptionscited by 4
  14. 2025EA3D: Online Open-World 3D Object Extraction from Streaming Videoscited by 4
  15. 2025SwiftVGGT: A Scalable Visual Geometry Grounded Transformer for Large-Scale Scenescited by 4
  16. 2026UFO-4D: Unposed Feedforward 4D Reconstruction from Two Imagescited by 4
  17. 2025Wanderland: Geometrically Grounded Simulation for Open-World Embodied AIcited by 3
  18. 2026S-MUSt3R: Sliding Multi-view 3D Reconstructioncited by 3
  19. 2025ROVER: Robust Loop Closure Verification with Trajectory Prior in Repetitive Environmentscited by 2
  20. 2026360DVO: Deep Visual Odometry for Monocular 360-Degree Cameracited by 2
  21. 2026VGGT-SLAM++cited by 2
  22. 2026VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motioncited by 2
  23. 2025BRIGHT-VO: Brightness-Guided Hybrid Transformer for Visual Odometry with Multi-modality Refinement Modulecited by 1
  24. 2025Dynamic Visual SLAM using a General 3D Priorcited by 1
  25. 2026SCE-SLAM: Scale-Consistent Monocular SLAM via Scene Coordinate Embeddingscited by 1
  26. 2026OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformercited by 1
  27. 2026End-to-End Spatial-Temporal Transformer for Real-time 4D HOI Reconstructioncited by 1
  28. 2026Online3R: Online Learning for Consistent Sequential Reconstruction Based on Geometry Foundation Modelcited by 1
  29. 2026SS3D: End2End Self-Supervised 3D from Web Videoscited by 1
  30. 2026MVOFormer: Flow-Semantic Transformer for Robust Monocular Visual Odometrycited by 1
  31. 2026UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimizationcited by 1
  32. 2026SLAMFormer-∞: Infinite SLAM Transformer for Unbounded Frontend and Backend Processingcited by 1
  33. 2024LGU-SLAM: Learnable Gaussian Uncertainty Matching with Deformable Correlation Sampling for Deep Visual SLAMcited by 0
  34. 2025Dropping the D: RGB-D SLAM Without the Depth Sensorcited by 0
  35. 2025DPVO-QAT++: Heterogeneous QAT and CUDA Kernel Fusion for High-Performance Deep Patch Visual Odometrycited by 0
  36. 2025ACE-SLAM: Scene Coordinate Regression for Neural Implicit Real-Time SLAMcited by 0
  37. 2026Loop Closure using AnyLoc Visual Place Recognition in DPV-SLAMcited by 0
  38. 2026Online Adaptation of Visual Odometry Frontends with Image-Conditioned Reinforcement Learningcited by 0

50 most cited of 68 All 68 (JSON)