# BAT3R: Bootstrapping Articulated 3D Reconstruction from 2D Image Collections

arXiv: https://arxiv.org/abs/2607.03891 · HTML: https://mlsanity.com/paper/2607.03891/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 44 of its 52 references that are in the map.
- First posted on arXiv 4 Jul 2026.

## Builds on (most cited first, 30 of 44)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [DUSt3R: Geometric 3D Vision Made Easy](https://mlsanity.com/paper/2312.14132/) (2023)
- [Objaverse: A Universe of Annotated 3D Objects](https://mlsanity.com/paper/2212.08051/) (2022)
- [Zero-1-to-3: Zero-shot One Image to 3D Object](https://mlsanity.com/paper/2303.11328/) (2023)
- [Objaverse-XL: A Universe of 10M+ 3D Objects](https://mlsanity.com/paper/2307.05663/) (2023)
- [Structured 3D Latents for Scalable and Versatile 3D Generation](https://mlsanity.com/paper/2412.01506/) (2024)
- [Wonder3D: Single Image to 3D using Cross-Domain Diffusion](https://mlsanity.com/paper/2310.15008/) (2023)
- [Learning Category-Specific Mesh Reconstruction from Image Collections](https://mlsanity.com/paper/1803.07549/) (2018)
- [3D Menagerie: Modeling the 3D shape and pose of animals](https://mlsanity.com/paper/1611.07700/) (2016)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers](https://mlsanity.com/paper/2312.09147/) (2023)
- [SAM 3D: 3Dfy Anything in Images](https://mlsanity.com/paper/2511.16624/) (2025)
- [BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion](https://mlsanity.com/paper/2306.16940/) (2023)
- [Text2Tex: Text-driven Texture Synthesis via Diffusion Models](https://mlsanity.com/paper/2303.11396/) (2023)
- [Atlas: End-to-End 3D Scene Reconstruction from Posed Images](https://mlsanity.com/paper/2003.10432/) (2020)
- [Native and Compact Structured Latents for 3D Generation](https://mlsanity.com/paper/2512.14692/) (2025)
- [Self-supervised Single-view 3D Reconstruction via Semantic Consistency](https://mlsanity.com/paper/2003.06473/) (2020)
- [4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface](https://mlsanity.com/paper/2105.01905/) (2021)
- [AP-10K: A Benchmark for Animal Pose Estimation in the Wild](https://mlsanity.com/paper/2108.12617/) (2021)
- [MagicPony: Learning Articulated 3D Animals in the Wild](https://mlsanity.com/paper/2211.12497/) (2022)
- [Shape and Viewpoint without Keypoints](https://mlsanity.com/paper/2007.10982/) (2020)
- [Articulation-aware Canonical Surface Mapping](https://mlsanity.com/paper/2004.00614/) (2020)
- [LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery](https://mlsanity.com/paper/2207.03434/) (2022)
- [Playing for 3D Human Recovery](https://mlsanity.com/paper/2110.07588/) (2021)
- [Canonical Surface Mapping via Geometric Cycle Consistency](https://mlsanity.com/paper/1907.10043/) (2019)
- [Learning the 3D Fauna of the Web](https://mlsanity.com/paper/2401.02400/) (2024)

## Abstract (arXiv)

3D reconstruction of articulated objects from a single image is challenging because large training datasets with paired image and 3D supervision are difficult to obtain. Recent point map-based methods achieve strong performance but rely on synthetic datasets rendered from manually created articulated 3D assets with carefully curated pose distributions. While camera viewpoints can be easily sampled, generating realistic object articulations remains costly and labor-intensive. We propose a training framework that reduces this requirement by leveraging unannotated 2D images collections with only a single rigged canonical mesh per category. Starting from a weak 3D shape predictor trained on canonical-pose renders, we iteratively estimate object articulation and camera pose by fitting the mesh to predicted point maps. The recovered articulations and viewpoints are then used to render updated synthetic training data, progressively improving the predictor. Despite using substantially weaker 3D supervision, our models achieve performance comparable with DualPM, which requires manually curated articulated training datasets.