Research map / 3D vision / Human pose estimation
Fish2Mesh Transformer: 3D Human Mesh Recovery from Egocentric Vision
Tianma Shen, Aditya Puranik, James Vong, Vrushabh Deogirikar, Ryan Fell, Julianna Dietrich, Maria Kyrarini, Christopher Kitts, David C. Jeong
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 Egocentric Position Embedding (ablation) | Fish2Mesh · ECHP | PA-MPJPE (mm): 92.448 -> 57.671 | Improved |
| add the proposed prompt-based dataset to training (ablation) | Fish2Mesh · ECHP | PA-MPJPE (mm): 71.446 -> 57.671 | Improved |
| add Egocentric Position Embedding (ablation) | Fish2Mesh · Ego4D | PA-MPJPE (mm): 90.111 -> 41.931 | Improved |
| add the proposed prompt-based dataset to training (ablation) | Fish2Mesh · Ego4D | PA-MPJPE (mm): 65.559 -> 41.931 | Improved |
| add Egocentric Position Embedding (ablation) | Fish2Mesh · Our dataset | PA-MPJPE (mm): 87.731 -> 37.242 | Improved |
| add the proposed prompt-based dataset to training (ablation) | Fish2Mesh · Our dataset | PA-MPJPE (mm): 60.446 -> 37.242 | Improved |
| add Egocentric Position Embedding (ablation) | Fish2Mesh · ECHP | PA-MPVPE (mm): 106.005 -> 75.322 | Improved |
| add the proposed prompt-based dataset to training (ablation) | Fish2Mesh · Ego4D | PA-MPVPE (mm): 87.529 -> 54.756 | Improved |
| Fish2Mesh versus EgoHMR (no fisheye handling, diffusion) | Fish2Mesh · Ego4D | PA-MPJPE (mm): 114.423 -> 41.931 | Improved |
| Fish2Mesh versus EgoHMR on EgoHMR's own dataset | Fish2Mesh · ECHP | PA-MPVPE (mm): 79.031 -> 75.322 | Improved |
Closest papers by meaning
- Scene-Aware Egocentric 3D Human Pose Estimation (CVPR 2023 · similarity 0.90)
- SelfPose: 3D Egocentric Pose Estimation From a Headset Mounted Camera (TPAMI 2020 · similarity 0.90)
- End-to-End Recovery of Human Shape and Pose (CVPR 2018 · similarity 0.90)
- Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement (CVPR 2024 · similarity 0.88)
- 3D Human Pose Perception from Egocentric Stereo Videos (CVPR 2024 · similarity 0.87)
- MeshPose: Unifying DensePose and 3D Body Mesh Reconstruction (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.
