Research map / 3D vision / Face and shape
ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections
Chun-Han Yao, Amit Raj, Wei-Chih Hung, Michael Rubinstein, Yuanzhen Li, Ming-Hsuan Yang, Varun Jampani
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add ARTIC3D diffusion-guided DASS pipeline | Hi-LASSIE · E-LASSIE Giraffe | PCK@0.05: 54.3 -> 58.0 | Improved |
| add ARTIC3D diffusion-guided DASS pipeline | Hi-LASSIE · E-LASSIE Elephant | PCK@0.05: 37.6 -> 39.8 | Improved |
| add ARTIC3D diffusion-guided DASS pipeline | Hi-LASSIE · LASSIE Kangaroo (clean) | PCK@0.05: 35.0 -> 36.7 | Improved |
| add naive SDS loss through encoder (Hi-LASSIE+) | Hi-LASSIE · E-LASSIE Giraffe | PCK@0.05: 54.3 -> 54.8 | No clear effect |
| add naive SDS loss through encoder (Hi-LASSIE+) | Hi-LASSIE · Pascal-Part Horse | PCK@0.1: 43.7 -> 43.3 | No clear effect |
| replace Hi-LASSIE with ARTIC3D | Hi-LASSIE · Pascal-Part Sheep | PCK@0.1: 29.9 -> 31.9 | Mixed |
| replace encoder-based SDS with decoder-based DASS (ablation) | Hi-LASSIE+ · E-LASSIE Penguin | PCK@0.05: 41.8 -> 43.8 | Improved |
| use ARTIC3D instead of Hi-LASSIE | Hi-LASSIE · E-LASSIE Elephant CLIP image-image | CLIP similarity: 80.0 -> 82.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Hi-LASSIE — Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery From Sparse Image Ensemble (CVPR 2023) · better on 22 of 22 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- BANMo: Building Animatable 3D Neural Models From Many Casual Videos (CVPR 2022 · similarity 0.90)
- Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery From Sparse Image Ensemble (CVPR 2023 · similarity 0.89)
- Learning Implicit Representation for Reconstructing Articulated Objects (ICLR 2024 · similarity 0.88)
- SAOR: Single-View Articulated Object Reconstruction (CVPR 2024 · similarity 0.87)
- MagicArticulate: Make Your 3D Models Articulation-Ready (CVPR 2025 · similarity 0.87)
- CAGE: Controllable Articulation GEneration (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
