Research map / 3D vision / Human pose estimation
DICArt: Advancing Category-level Articulated Object Pose Estimation in Discrete State-Spaces
Li Zhang, Mingyu Mei, Ailing Wang, Xianhui Meng, Yan Zhong, Xinyuan Song, Liu Liu, Rujing Wang, Zaixing He, Cewu Lu
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 |
|---|---|---|---|
| use discrete instead of continuous diffusion (ablation) | DICArt · ArtImage Drawer | rotation error: 3.1 -> 1.7 | Improved |
| use discrete instead of continuous diffusion (ablation) | DICArt · ArtImage Drawer | translation error: 0.143 -> 0.072 | Improved |
| add reformulated denoising with flexible flow decider (ablation) | DICArt · ArtImage Drawer | rotation error: 4.0 -> 1.7 | Improved |
| add reformulated denoising with flexible flow decider (ablation) | DICArt · ArtImage Drawer | translation error: 0.128 -> 0.072 | Improved |
| increase self-occlusion from 0-40% to 80-100% visibility bins (ablation) | DICArt · ArtImage Drawer | rotation error: 1.8 -> 1.9 | No clear effect |
| increase occlusion level (visibility bins) (ablation) | DICArt · ArtImage Drawer | translation error: 0.089 -> 0.107 | Mixed |
| hierarchical kinematic coupling versus part-wise estimation | DICArt · ArtImage Dishwasher | child-part pose error | Improved |
| DICArt versus A-NCSH on axis angle error | DICArt · ArtImage Laptop | axis angle error: 1.7 -> 0.8 | Improved |
| DICArt versus A-NCSH on axis distance error | DICArt · ArtImage Laptop | axis distance error: 0.09 -> 0.04 | Mixed |
| DICArt versus A-NCSH on part 1 translation | DICArt · RobotArm part 1 | translation error: 0.012 -> 0.011 | No clear effect |
| DICArt versus ReArtNet on Scissors translation | DICArt · ReArtMix Scissors | translation error: 0.009, 0.015 -> 0.008, 0.011 | Mixed |
Closest papers by meaning
- DiffPose: Multi-hypothesis Human Pose Estimation using Diffusion Models (ICCV 2023 · similarity 0.90)
- Generative Category-level Object Pose Estimation via Diffusion Models (NeurIPS 2023 · similarity 0.90)
- $\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation (NeurIPS 2024 · similarity 0.88)
- EfficientCAPER: An End-to-End Framework for Fast and Robust Category-Level Articulated Object Pose Estimation (NeurIPS 2024 · similarity 0.87)
- Object Pose Estimation via the Aggregation of Diffusion Features (CVPR 2024 · similarity 0.87)
- Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser (AAAI 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.
