# Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble

arXiv: https://arxiv.org/abs/2212.11042 · HTML: https://mlsanity.com/paper/2212.11042/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 46 references that are in the map.
- First posted on arXiv 21 Dec 2022.

## Builds on (most cited first, 30 of 37)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [NeRD: Neural Reflectance Decomposition from Image Collections](https://mlsanity.com/paper/2012.03918/) (2020)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relighting](https://mlsanity.com/paper/2104.00674/) (2021)
- [Deep ViT Features as Dense Visual Descriptors](https://mlsanity.com/paper/2112.05814/) (2021)
- [3D Menagerie: Modeling the 3D shape and pose of animals](https://mlsanity.com/paper/1611.07700/) (2016)
- [Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts](https://mlsanity.com/paper/1406.2031/) (2014)
- [Splicing ViT Features for Semantic Appearance Transfer](https://mlsanity.com/paper/2201.00424/) (2022)
- [Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition](https://mlsanity.com/paper/2110.14373/) (2021)
- [BANMo: Building Animatable 3D Neural Models from Many Casual Videos](https://mlsanity.com/paper/2112.12761/) (2021)
- [Learning Shape Abstractions by Assembling Volumetric Primitives](https://mlsanity.com/paper/1612.00404/) (2016)
- [BACON: Band-limited Coordinate Networks for Multiscale Scene Representation](https://mlsanity.com/paper/2112.04645/) (2021)
- [NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild](https://mlsanity.com/paper/2110.07604/) (2021)
- [Self-supervised Single-view 3D Reconstruction via Semantic Consistency](https://mlsanity.com/paper/2003.06473/) (2020)
- [LASR: Learning Articulated Shape Reconstruction from a Monocular Video](https://mlsanity.com/paper/2105.02976/) (2021)
- [Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"](https://mlsanity.com/paper/1908.07201/) (2019)
- [Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks](https://mlsanity.com/paper/2103.10429/) (2021)
- [SCOPS: Self-Supervised Co-Part Segmentation](https://mlsanity.com/paper/1905.01298/) (2019)
- [Shape and Viewpoint without Keypoints](https://mlsanity.com/paper/2007.10982/) (2020)
- [SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections](https://mlsanity.com/paper/2205.15768/) (2022)
- [Articulation-aware Canonical Surface Mapping](https://mlsanity.com/paper/2004.00614/) (2020)
- [Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image](https://mlsanity.com/paper/2004.01176/) (2020)
- [LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery](https://mlsanity.com/paper/2207.03434/) (2022)
- [Shelf-Supervised Mesh Prediction in the Wild](https://mlsanity.com/paper/2102.06195/) (2021)
- [Deep Feature Factorization For Concept Discovery](https://mlsanity.com/paper/1806.10206/) (2018)
- [Canonical Surface Mapping via Geometric Cycle Consistency](https://mlsanity.com/paper/1907.10043/) (2019)
- [Unsupervised Part Discovery from Contrastive Reconstruction](https://mlsanity.com/paper/2111.06349/) (2021)
- [Online Adaptation for Consistent Mesh Reconstruction in the Wild](https://mlsanity.com/paper/2012.03196/) (2020)
- [BARC: Learning to Regress 3D Dog Shape from Images by Exploiting Breed Information](https://mlsanity.com/paper/2203.15536/) (2022)

## Built on by (most cited first, 30 of 31)

- [Learning the 3D Fauna of the Web](https://mlsanity.com/paper/2401.02400/) (2024)
- [Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion](https://mlsanity.com/paper/2304.10535/) (2023)
- [Recent Trends in 3D Reconstruction of General Non-Rigid Scenes](https://mlsanity.com/paper/2403.15064/) (2024)
- [ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections](https://mlsanity.com/paper/2306.04619/) (2023)
- [Ponymation: Learning Articulated 3D Animal Motions from Unlabeled Online Videos](https://mlsanity.com/paper/2312.13604/) (2023)
- [OmniMotionGPT: Animal Motion Generation with Limited Data](https://mlsanity.com/paper/2311.18303/) (2023)
- [SAOR: Single-View Articulated Object Reconstruction](https://mlsanity.com/paper/2303.13514/) (2023)
- [Template-free Articulated Neural Point Clouds for Reposable View Synthesis](https://mlsanity.com/paper/2305.19065/) (2023)
- [Survey on Modeling of Human-made Articulated Objects](https://mlsanity.com/paper/2403.14937/) (2024)
- [Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis](https://mlsanity.com/paper/2412.05570/) (2024)
- [Articulated Kinematics Distillation from Video Diffusion Models](https://mlsanity.com/paper/2504.01204/) (2025)
- [DreaMo: Articulated 3D Reconstruction From A Single Casual Video](https://mlsanity.com/paper/2312.02617/) (2023)
- [AWOL: Analysis WithOut synthesis using Language](https://mlsanity.com/paper/2404.03042/) (2024)
- [S3O: A Dual-Phase Approach for Reconstructing Dynamic Shape and Skeleton of Articulated Objects from Single Monocular Video](https://mlsanity.com/paper/2405.12607/) (2024)
- [ToMiE: Towards Explicit Exoskeleton for the Reconstruction of Complicated 3D Human Avatars](https://mlsanity.com/paper/2410.08082/) (2024)
- [Common3D: Self-Supervised Learning of 3D Morphable Models for Common Objects in Neural Feature Space](https://mlsanity.com/paper/2504.21749/) (2025)
- [Category-Agnostic Neural Object Rigging](https://mlsanity.com/paper/2505.20283/) (2025)
- [Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images](https://mlsanity.com/paper/2410.03438/) (2024)
- [Birth and Death of a Rose](https://mlsanity.com/paper/2412.05278/) (2024)
- [4D-Animal: Freely Reconstructing Animatable 3D Animals from Videos](https://mlsanity.com/paper/2507.10437/) (2025)
- [Learning Articulated Shape with Keypoint Pseudo-labels from Web Images](https://mlsanity.com/paper/2304.14396/) (2023)
- [Model-based Metric 3D Shape and Motion Reconstruction of Wild Bottlenose Dolphins in Drone-Shot Videos](https://mlsanity.com/paper/2504.15782/) (2025)
- [Advances and Trends in the 3D Reconstruction of the Shape and Motion of Animals](https://mlsanity.com/paper/2508.16062/) (2025)
- [4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video](https://mlsanity.com/paper/2603.10125/) (2026)
- [PRIMA: Boosting Animal Mesh Recovery with Biological Priors and Test-Time Adaptation](https://mlsanity.com/paper/2606.02366/) (2026)
- [MotionDreamer: Exploring Semantic Video Diffusion features for Zero-Shot 3D Mesh Animation](https://mlsanity.com/paper/2405.20155/) (2024)
- [YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals](https://mlsanity.com/paper/2406.16273/) (2024)
- [Progressive Pose-Guided 4D Animal Reconstruction from Monocular Video](https://mlsanity.com/paper/2607.00157/) (2026)
- [CORGI: Consistency-Aware 3D Dog Reconstruction from a Single Image in the Wild](https://mlsanity.com/paper/2607.00321/) (2026)
- [BAT3R: Bootstrapping Articulated 3D Reconstruction from 2D Image Collections](https://mlsanity.com/paper/2607.03891/) (2026)

## Abstract (arXiv)

Automatically estimating 3D skeleton, shape, camera viewpoints, and part articulation from sparse in-the-wild image ensembles is a severely under-constrained and challenging problem. Most prior methods rely on large-scale image datasets, dense temporal correspondence, or human annotations like camera pose, 2D keypoints, and shape templates. We propose Hi-LASSIE, which performs 3D articulated reconstruction from only 20-30 online images in the wild without any user-defined shape or skeleton templates. We follow the recent work of LASSIE that tackles a similar problem setting and make two significant advances. First, instead of relying on a manually annotated 3D skeleton, we automatically estimate a class-specific skeleton from the selected reference image. Second, we improve the shape reconstructions with novel instance-specific optimization strategies that allow reconstructions to faithful fit on each instance while preserving the class-specific priors learned across all images. Experiments on in-the-wild image ensembles show that Hi-LASSIE obtains higher fidelity state-of-the-art 3D reconstructions despite requiring minimum user input.