mlsanityData to 7 Oct 2026

TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos

arXiv 2403.17346 ↗First posted 26 Mar 2024cs.CVcited by 105

Not on the map. Why?

Abstract (arXiv)

We propose TRAM, a two-stage method to reconstruct a human's global trajectory and motion from in-the-wild videos. TRAM robustifies SLAM to recover the camera motion in the presence of dynamic humans and uses the scene background to derive the motion scale. Using the recovered camera as a metric-scale reference frame, we introduce a video transformer model (VIMO) to regress the kinematic body motion of a human. By composing the two motions, we achieve accurate recovery of 3D humans in the world space, reducing global motion errors by a large margin from prior work. https://yufu-wang.github.io/tram4d/

Key facts. Cited by 105 papers in the map (data through 7 Oct 2026). Builds on 80 of its 102 references that are in the map. First posted on arXiv 26 Mar 2024.

Builds on

80 of 102 references.

References · 80

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2023Segment Anythingcited by 8,158
  5. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  6. 2021ViViT: A Video Vision Transformercited by 1,610
  7. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,600
  8. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  9. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,208
  10. 2021Scaling Vision Transformerscited by 993
  11. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  12. 2017End-to-end Recovery of Human Shape and Posecited by 883
38 more
  1. 2016ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Camerascited by 801
  2. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 692
  3. 2023Scaling Vision Transformers to 22 Billion Parameterscited by 690
  4. 2024SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilitiescited by 679
  5. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  6. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  7. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 625
  8. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 615
  9. 2021Action-Conditioned 3D Human Motion Synthesis with Transformer VAEcited by 497
  10. 2016Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervisioncited by 493
  11. 2022ViTPose: Simple Vision Transformer Baselines for Human Pose Estimationcited by 450
  12. 2020End-to-End Human Pose and Mesh Reconstruction with Transformerscited by 417
  13. 2016Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Agecited by 405
  14. 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
  15. 2023Humans in 4D: Reconstructing and Tracking Humans with Transformerscited by 344
  16. 2021PARE: Part Attention Regressor for 3D Human Body Estimationcited by 334
  17. 2021HuMoR: 3D Human Motion Model for Robust Pose Estimationcited by 319
  18. 2018Learning 3D Human Dynamics from Videocited by 315
  19. 2020HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimationcited by 304
  20. 2020I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Imagecited by 274
  21. 2019Convolutional Mesh Regression for Single-Image Human Shape Reconstructioncited by 270
  22. 2021Mesh Graphormercited by 264
  23. 2021PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loopcited by 250
  24. 2020Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Posecited by 248
  25. 2022CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimationcited by 237
  26. 2023BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motioncited by 229
  27. 2020Monocular, One-stage, Regression of Multiple 3D Peoplecited by 216
  28. 2023WHAM: Reconstructing World-grounded Humans with Accurate 3D Motioncited by 200
  29. 2018Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimationcited by 185
  30. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  31. 2020Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Videocited by 162
  32. 2021GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Camerascited by 151
  33. 2021Putting People in their Place: Monocular Regression of 3D People in Depthcited by 141
  34. 2023Decoupling Human and Camera Motion from Videos in the Wildcited by 140
  35. 2021Human POSEitioning System (HPS): 3D Human Pose Estimation and Self-localization in Large Scenes from Body-Mounted Sensorscited by 137
  36. 2023Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusioncited by 137
  37. 2020Coherent Reconstruction of Multiple Humans from a Single Imagecited by 136
  38. 2021EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devicescited by 136

50 most cited of 80 All 80 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 13; 2025: 46; 2026: 46.

105 papers.

Sort:

By area:

  1. 2025ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skillscited by 104
  2. 2025PromptHMR: Promptable Human Mesh Recoverycited by 70
  3. 2024HumanVid: Demystifying Training Data for Camera-controllable Human Image Animationcited by 63
  4. 2025HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videoscited by 62
  5. 2026SAM 3D Body: Robust Full-Body Human Mesh Recoverycited by 61
  6. 2025Visual Imitation Enables Contextual Humanoid Controlcited by 57
  7. 2025Humanoid-VLA: Towards Universal Humanoid Control with Visual Integrationcited by 43
  8. 2025GENMO: A GENeralist Model for Human MOtioncited by 43
  9. 2025Human3R: Everyone Everywhere All at Oncecited by 35
  10. 2024Reconstructing People, Places, and Camerascited by 31
  11. 2025HUMOTO: A 4D Dataset of Mocap Human Object Interactionscited by 30
  12. 2024SMPLOlympics: Sports Environments for Physically Simulated Humanoidscited by 29
38 more
  1. 2025Joint Optimization for 4D Human-Scene Reconstruction in the Wildcited by 29
  2. 2025A Survey on Human Interaction Motion Generationcited by 25
  3. 2025HuB: Learning Extreme Humanoid Balancecited by 21
  4. 2025BEDLAM2.0: Synthetic Humans and Cameras in Motioncited by 21
  5. 2025Multi-identity Human Image Animation with Structural Video Diffusioncited by 13
  6. 2025CoMotion: Concurrent Multi-person 3D Motioncited by 13
  7. 2025Reconstructing 4D Spatial Intelligence: A Surveycited by 13
  8. 2025PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Imagecited by 13
  9. 2026Video Generation Models are General-Purpose Vision Learnerscited by 12
  10. 2025RealisMotion: Decomposed Human Motion Control and Video Generation in the World Spacecited by 10
  11. 2024DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priorscited by 9
  12. 2025Pulp Motion: Framing-aware multimodal camera and human motion generationcited by 8
  13. 2025SAM-Body4D: Training-Free 4D Human Body Mesh Recovery from Videoscited by 8
  14. 2025MoCapAnything: Unified 3D Motion Capture for Arbitrary Skeletons from Monocular Videoscited by 8
  15. 2025Zero-Shot Human-Object Interaction Synthesis with Multimodal Priorscited by 7
  16. 2025Perceiving and Acting in First-Person: A Dataset and Benchmark for Egocentric Human-Object-Human Interactionscited by 7
  17. 2026UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Passcited by 7
  18. 2024Motion-Aware Animatable Gaussian Avatars Deblurringcited by 6
  19. 2025Learning to Ball: Composing Policies for Long-Horizon Basketball Movescited by 6
  20. 2026DuoMo: Dual Motion Diffusion for World-Space Human Reconstructioncited by 6
  21. 2024CondiMen: Conditional Multi-Person Mesh Recoverycited by 5
  22. 2025SMF: Template-free and Rig-free Animation Transfer using Kinetic Codescited by 5
  23. 2025AnimateAnywhere: Rouse the Background in Human Image Animationcited by 5
  24. 2025PhysHMR: Learning Humanoid Control Policies from Vision for Physically Plausible Human Motion Reconstructioncited by 5
  25. 2025From Generated Human Videos to Physically Plausible Robot Trajectoriescited by 5
  26. 2026MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstructioncited by 5
  27. 2024Motion Capture from Inertial and Vision Sensorscited by 4
  28. 2024A Plug-and-Play Physical Motion Restoration Approach for In-the-Wild High-Difficulty Motionscited by 4
  29. 2025DAViD: Modeling Dynamic Affordance of 3D Objects Using Pre-trained Video Diffusion Modelscited by 4
  30. 2025HumanMM: Global Human Motion Recovery from Multi-shot Videoscited by 4
  31. 2026ZEST: Zero-shot Embodied Skill Transfer for Athletic Robot Controlcited by 4
  32. 2026Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recoverycited by 4
  33. 2026OnlineHMR: Video-based Online World-Grounded Human Mesh Recoverycited by 4
  34. 2026THFM: A Unified Video Foundation Model for 4D Human Perception and Beyondcited by 4
  35. 2025MetricHMSR:Metric Human Mesh and Scene Recovery from Monocular Imagescited by 3
  36. 2025DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Videocited by 3
  37. 2025Group Inertial Poser: Multi-Person Pose and Global Translation from Sparse Inertial Sensors and Ultra-Wideband Rangingcited by 3
  38. 2025Efficient and Scalable Monocular Human-Object Interaction Motion Reconstructioncited by 3

50 most cited of 105 All 105 (JSON)