Research map / 3D vision / Human pose estimation
Zero-shot Human Pose Estimation using Diffusion-based Inverse solvers
Sahil Bhandary Karnoor, Romit Roy Choudhury
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 InPose (rotation-only CFG plus location inverse guidance) instead of location-conditioned baselines | sparse 3-point pose estimation · AMASS Protocol 1, upper body x1.4 | MPJPE: 13.40 -> 9.15 (vs BoDiffusion(Global)) | Improved |
| use InPose on the default training body shape | sparse 3-point pose estimation · AMASS Protocol 1, default shape | MPJPE: 4.92 -> 7.64 (vs AvatarJLM) | Hurt |
| use InPose on lower-body error with scaled shapes | sparse 3-point pose estimation · AMASS Protocol 1, arms x1.4 torso x0.7 | LPE: 11.98 -> 14.6 (vs BoDiffusion(Global)) | Hurt |
| add head translation as an input to the CFG score model (ablation) | InPose · AMASS Protocol 1, upper body x1.17 | MPJPE: 8.25 -> 5.92 | Improved |
| add head translation as an input to the CFG score model (ablation) | InPose · AMASS Protocol 1, upper body x1.17 | LPE: 15.37 -> 11.29 | Improved |
| use 6D rotation representation instead of raw rotation matrices (ablation) | diffusion pose generation · unconditional UNET diffusion samples | mesh jitter (qualitative) | Improved |
| add inverse guidance with locations rather than conditioning on locations (noise robustness) | InPose · location measurement noise, default shape | location error | Improved |
Closest papers by meaning
- $\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation (NeurIPS 2024 · similarity 0.88)
- DiffusionRegPose: Enhancing Multi-Person Pose Estimation using a Diffusion-Based End-to-End Regression Approach (CVPR 2024 · similarity 0.87)
- Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser (AAAI 2024 · similarity 0.87)
- Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models (ICLR 2024 · similarity 0.86)
- Object Pose Estimation via the Aggregation of Diffusion Features (CVPR 2024 · similarity 0.86)
- DiffusionPoser: Real-time Human Motion Reconstruction From Arbitrary Sparse Sensors Using Autoregressive Diffusion (CVPR 2024 · similarity 0.86)
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.
