mlsanityData to 14 Oct 2026

LASR: Learning Articulated Shape Reconstruction from a Monocular Video

arXiv 2105.02976 ↗First posted 6 May 2021cs.CV cs.GRcited by 116

Not on the map. Why?

Abstract (arXiv)

Remarkable progress has been made in 3D reconstruction of rigid structures from a video or a collection of images. However, it is still challenging to reconstruct nonrigid structures from RGB inputs, due to its under-constrained nature. While template-based approaches, such as parametric shape models, have achieved great success in modeling the "closed world" of known object categories, they cannot well handle the "open-world" of novel object categories or outlier shapes. In this work, we introduce a template-free approach to learn 3D shapes from a single video. It adopts an analysis-by-synthesis strategy that forward-renders object silhouette, optical flow, and pixel values to compare with video observations, which generates gradients to adjust the camera, shape and motion parameters. Without using a category-specific shape template, our method faithfully reconstructs nonrigid 3D structures from videos of human, animals, and objects of unknown classes. Code will be available at lasr-google.github.io .

Key facts. Cited by 116 papers in the map (data through 14 Oct 2026). Builds on 31 of its 58 references that are in the map. First posted on arXiv 6 May 2021.

Builds on

31 of 58 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
  6. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  7. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  8. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  9. 2020Accelerating 3D Deep Learning with PyTorch3Dcited by 784
  10. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  11. 2019VIBE: Video Inference for Human Body Pose and Shape Estimationcited by 620
  12. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
19 more
  1. 2019PointRend: Image Segmentation as Renderingcited by 440
  2. 2019Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoningcited by 420
  3. 2018Learning Category-Specific Mesh Reconstruction from Image Collectionscited by 317
  4. 20163D Menagerie: Modeling the 3D shape and pose of animalscited by 312
  5. 2018Neighbourhood Consensus Networkscited by 174
  6. 2018Monocular Total Capture: Posing Face, Body, and Hands in the Wildcited by 162
  7. 2020Self-supervised Single-view 3D Reconstruction via Semantic Consistencycited by 127
  8. 2019Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"cited by 106
  9. 2018Creatures great and SMAL: Recovering the shape and motion of animals from videocited by 84
  10. 2016Universal Correspondence Networkcited by 82
  11. 2020Articulation-aware Canonical Surface Mappingcited by 81
  12. 2020Who Left the Dogs Out? 3D Animal Reconstruction with Expectation Maximization in the Loopcited by 81
  13. 2019C3DPO: Canonical 3D Pose Networks for Non-Rigid Structure From Motioncited by 61
  14. 2018Robust Watertight Manifold Surface Generation Method for ShapeNet Modelscited by 59
  15. 2020Online Adaptation for Consistent Mesh Reconstruction in the Wildcited by 51
  16. 2020Implicit Mesh Reconstruction from Unannotated Image Collectionscited by 49
  17. 20203D Bird Reconstruction: a Dataset, Model, and Shape Recovery from a Single Viewcited by 40
  18. 2019Deep Non-Rigid Structure from Motioncited by 38
  19. 2020Deep NRSfM++: Towards Unsupervised 2D-3D Lifting in the Wildcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 27; 2023: 24; 2024: 30; 2025: 18; 2026: 13.

116 papers.

Sort:

By area:

  1. 2022Kubric: A scalable dataset generatorcited by 381
  2. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 250
  3. 2022Particle Video Revisited: Tracking Through Occlusions Using Point Trajectoriescited by 217
  4. 2022Monocular Dynamic View Synthesis: A Reality Checkcited by 200
  5. 2021BANMo: Building Animatable 3D Neural Models from Many Casual Videoscited by 197
  6. 2023Tracking Everything Everywhere All at Oncecited by 193
  7. 2024MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffoldscited by 179
  8. 2022Ditto: Building Digital Twins of Articulated Objects from Interactioncited by 156
  9. 2024L4GM: Large 4D Gaussian Reconstruction Modelcited by 144
  10. 2021NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wildcited by 136
  11. 2023State of the Art on Diffusion Models for Visual Computingcited by 127
  12. 2022MagicPony: Learning Articulated 3D Animals in the Wildcited by 112
38 more
  1. 2024URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Imagescited by 111
  2. 2024GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creationcited by 100
  3. 2022Full-Body Articulated Human-Object Interactioncited by 78
  4. 2025ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splattingcited by 67
  5. 2022LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discoverycited by 66
  6. 2023CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objectscited by 64
  7. 2023MFT: Long-Term Tracking of Every Pixelcited by 62
  8. 2021DOVE: Learning Deformable 3D Objects by Watching Videoscited by 61
  9. 2024Learning the 3D Fauna of the Webcited by 59
  10. 2023Visibility Aware Human-Object Interaction Tracking from Single RGB Cameracited by 58
  11. 2022Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Cameracited by 57
  12. 2022SparsePose: Sparse-View Camera Pose Regression and Refinementcited by 53
  13. 2022Self-supervised Neural Articulated Shape and Appearance Modelscited by 51
  14. 2023Reconstructing Animatable Categories from Videoscited by 47
  15. 2024REACTO: Reconstructing Articulated Objects from a Single Videocited by 45
  16. 2022Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesiscited by 41
  17. 2023Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusioncited by 38
  18. 2024Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfelscited by 38
  19. 2022CASA: Category-agnostic Skeletal Animal Reconstructioncited by 35
  20. 2022Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemblecited by 31
  21. 2022State of the Art in Dense Monocular Non-Rigid 3D Reconstructioncited by 30
  22. 2022Common Pets in 3D: Dynamic New-View Synthesis of Real-Life Deformable Categoriescited by 29
  23. 2022Cross-Modal 3D Shape Generation and Manipulationcited by 28
  24. 2023Flexible Techniques for Differentiable Rendering with 3D Gaussianscited by 28
  25. 2024Recent Trends in 3D Reconstruction of General Non-Rigid Scenescited by 28
  26. 2022In-Hand 3D Object Scanning from an RGB Sequencecited by 27
  27. 2024Animal Avatars: Reconstructing Animatable 3D Animals from Casual Videoscited by 26
  28. 2022Unbiased 4D: Monocular 4D Reconstruction with a Neural Deformation Modelcited by 25
  29. 2023NAP: Neural 3D Articulation Priorcited by 25
  30. 2022φ-SfT: Shape-from-Template with a Physics-Based Deformation Modelcited by 23
  31. 2024InterTrack: Tracking Human Object Interaction without Object Templatescited by 23
  32. 2022Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wildcited by 22
  33. 2023ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collectionscited by 22
  34. 2024Dynamic Gaussians Mesh: Consistent Mesh Reconstruction from Dynamic Scenescited by 22
  35. 2023Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videoscited by 21
  36. 2023Total-Recon: Deformable Scene Reconstruction for Embodied View Synthesiscited by 20
  37. 2023OmniMotionGPT: Animal Motion Generation with Limited Datacited by 20
  38. 2022Motion Guided Deep Dynamic 3D Garmentscited by 19

50 most cited of 116 All 116 (JSON)