# ScrewSplat: An End-to-End Method for Articulated Object Recognition

arXiv: https://arxiv.org/abs/2508.02146 · HTML: https://mlsanity.com/paper/2508.02146/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 52 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Builds on (most cited first, 30 of 38)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021)
- [SAPIEN: A SimulAted Part-based Interactive ENvironment](https://mlsanity.com/paper/2003.08515/) (2020)
- [Neural 3D Mesh Renderer](https://mlsanity.com/paper/1711.07566/) (2017)
- [Category-Level Articulated Object Pose Estimation](https://mlsanity.com/paper/1912.11913/) (2019)
- [Ditto: Building Digital Twins of Articulated Objects from Interaction](https://mlsanity.com/paper/2202.08227/) (2022)
- [BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects](https://mlsanity.com/paper/2303.14158/) (2023)
- [Dex-NeRF: Using a Neural Radiance Field to Grasp Transparent Objects](https://mlsanity.com/paper/2110.14217/) (2021)
- [PARIS: Part-level Reconstruction and Motion Analysis for Articulated Objects](https://mlsanity.com/paper/2308.07391/) (2023)
- [A-SDF: Learning Disentangled Signed Distance Functions for Articulated Shape Representation](https://mlsanity.com/paper/2104.07645/) (2021)
- [Learning to Infer Implicit Surfaces without 3D Supervision](https://mlsanity.com/paper/1911.00767/) (2019)
- [Articulate-Anything: Automatic Modeling of Articulated Objects via a Vision-Language Foundation Model](https://mlsanity.com/paper/2410.13882/) (2024)
- [Shape Completion Enabled Robotic Grasping](https://mlsanity.com/paper/1609.08546/) (2016)
- [ScrewNet: Category-Independent Articulation Model Estimation From Depth Images Using Screw Theory](https://mlsanity.com/paper/2008.10518/) (2020)
- [Neural Implicit Representation for Building Digital Twins of Unknown Articulated Objects](https://mlsanity.com/paper/2404.01440/) (2024)
- [GraspNeRF: Multiview-based 6-DoF Grasp Detection for Transparent and Specular Objects Using Generalizable NeRF](https://mlsanity.com/paper/2210.06575/) (2022)
- [ArtGS: Building Interactable Replicas of Complex Articulated Objects via Gaussian Splatting](https://mlsanity.com/paper/2502.19459/) (2025)
- [CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects](https://mlsanity.com/paper/2303.15782/) (2023)
- [CLA-NeRF: Category-Level Articulated Neural Radiance Field](https://mlsanity.com/paper/2202.00181/) (2022)
- [Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction](https://mlsanity.com/paper/2409.18121/) (2024)
- [Self-supervised Neural Articulated Shape and Appearance Models](https://mlsanity.com/paper/2205.08525/) (2022)
- [Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery](https://mlsanity.com/paper/2105.01047/) (2021)
- [Ditto in the House: Building Articulation Models of Indoor Scenes through Interactive Perception](https://mlsanity.com/paper/2302.01295/) (2023)
- [Visual Identification of Articulated Object Parts](https://mlsanity.com/paper/2012.00284/) (2020)
- [Iterative Residual Policy: for Goal-Conditioned Dynamic Manipulation of Deformable Objects](https://mlsanity.com/paper/2203.00663/) (2022)
- [ArticulatedGS: Self-supervised Digital Twin Modeling of Articulated Objects using 3D Gaussian Splatting](https://mlsanity.com/paper/2503.08135/) (2025)
- [Learning Continuous 3D Reconstructions for Geometrically Aware Grasping](https://mlsanity.com/paper/1910.00983/) (2019)

## Built on by (most cited first, 9 of 9)

- [GaussianArt: Unified Modeling of Geometry and Motion for Articulated Objects](https://mlsanity.com/paper/2508.14891/) (2025)
- [Articulated 3D Scene Graphs for Open-World Mobile Manipulation](https://mlsanity.com/paper/2602.16356/) (2026)
- [Advances in 4D Representation: Geometry, Motion, and Interaction](https://mlsanity.com/paper/2510.19255/) (2025)
- [UniArt: Unified 3D Representation for Generating 3D Articulated Objects with Open-Set Articulation](https://mlsanity.com/paper/2511.21887/) (2025)
- [PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos](https://mlsanity.com/paper/2603.25539/) (2026)
- [LTGS: Long-Term Gaussian Scene Chronology From Sparse View Updates](https://mlsanity.com/paper/2510.09881/) (2025)
- [ArtMesh: Part-Aware Articulated Mesh Fields with Motion-Consistent Dynamics](https://mlsanity.com/paper/2605.16582/) (2026)
- [ArtSplat: Feed-Forward Articulated 3D Gaussian Splatting from Sparse Multi-State Uncalibrated Views](https://mlsanity.com/paper/2605.24304/) (2026)
- [StructureGS: Structure-aware Gaussian Splatting for Articulated Object Reconstruction](https://mlsanity.com/paper/2607.26889/) (2026)

## Abstract (arXiv)

Articulated object recognition -- the task of identifying both the geometry and kinematic joints of objects with movable parts -- is essential for enabling robots to interact with everyday objects such as doors and laptops. However, existing approaches often rely on strong assumptions, such as a known number of articulated parts; require additional inputs, such as depth images; or involve complex intermediate steps that can introduce potential errors -- limiting their practicality in real-world settings. In this paper, we introduce ScrewSplat, a simple end-to-end method that operates solely on RGB observations. Our approach begins by randomly initializing screw axes, which are then iteratively optimized to recover the object's underlying kinematic structure. By integrating with Gaussian Splatting, we simultaneously reconstruct the 3D geometry and segment the object into rigid, movable parts. We demonstrate that our method achieves state-of-the-art recognition accuracy across a diverse set of articulated objects, and further enables zero-shot, text-guided manipulation using the recovered kinematic model. See the project website at: https://screwsplat.github.io.