Research map / 3D vision / Human pose estimation
Shoe Style-Invariant and Ground-Aware Learning for Dense Foot Contact Estimation
Daniel Sungho Jung, Kyoung Mu Lee
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 progressive low-level style randomization (ablation) | FECO · MMVP | F1-score: 0.555 -> 0.577 | Improved |
| add shoe content randomization alone (ablation) | FECO · MMVP | F1-score: 0.522 -> 0.531 | Improved |
| add shoe style randomization alone (ablation) | FECO · MMVP | F1-score: 0.522 -> 0.554 | Improved |
| add both content and style randomization (ablation) | FECO · MMVP | F1-score: 0.522 -> 0.577 | Improved |
| add ground normal supervision (ablation) | FECO · MMVP | F1-score: 0.506 -> 0.527 | Improved |
| add pixel height map supervision (ablation) | FECO · MMVP | F1-score: 0.527 -> 0.569 | Improved |
| add spatial attention fusion of ground and randomized features (ablation) | FECO · MMVP | F1-score: 0.569 -> 0.577 | Improved |
| add COFE dataset to training (ablation) | FECO · COFE test | F1-score: 0.450 -> 0.515 | Improved |
| use shoe style-content randomization instead of SagNets | FECO · MMVP | F1-score: 0.511 -> 0.577 | Improved |
| use shoe style-content randomization instead of LatentDR | FECO · MMVP | F1-score: 0.542 -> 0.577 | Improved |
| use ViT-H backbone instead of ResNet-152 | FECO · MMVP | F1-score: 0.533 -> 0.577 | Improved |
| use ViT-H backbone instead of ViT-B | FECO · MMVP | F1-score: 0.574 -> 0.577 | Improved |
Closest papers by meaning
- DECO: Dense Estimation of 3D Human-Scene Contact In The Wild (ICCV 2023 · similarity 0.86)
- MMVP: A Multimodal MoCap Dataset with Vision and Pressure Sensors (CVPR 2024 · similarity 0.85)
- Learning Dense Hand Contact Estimation from Imbalanced Data (NeurIPS 2025 · similarity 0.84)
- ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On (NeurIPS 2025 · similarity 0.83)
- Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images (AAAI 2024 · similarity 0.82)
- On Denoising Walking Videos for Gait Recognition (CVPR 2025 · similarity 0.81)
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.
