Research map / 3D vision / Human pose estimation
Deep Deformation Network for Object Landmark Localization
Xiang Yu, Feng Zhou, Manmohan Chandraker
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 PTN refinement on top of SBN (ablation) | SBN · Helen | PCK@0.05: 51.4 -> 85.2 | Improved |
| add PTN refinement on top of SBN (ablation) | SBN · iBug | PCK@0.05: 22.6 -> 56.6 | Improved |
| add SBN initialization before PTN (ablation) | PTN · Helen | PCK@0.05: 81.4 -> 85.2 | Improved |
| add SBN initialization before PTN (ablation) | PTN · iBug | PCK@0.05: 49.1 -> 56.6 | Improved |
| add SBN initialization before PTN (ablation) | PTN · LFPW | PCK@0.10: 91.3 -> 91.6 | Improved |
| use TPS non-rigid warp instead of affine transformation (ablation) | a-DDN · Helen | PCK@0.05: 67.8 -> 85.2 | Improved |
| use TPS non-rigid warp instead of affine transformation (ablation) | a-DDN · iBug | PCK@0.05: 38.7 -> 56.6 | Improved |
| use TPS non-rigid warp instead of affine transformation (ablation) | a-DDN · LSP | mean PCK@0.2: 68.3 -> 84.3 | Improved |
| replace cGPRT with DDN | cGPRT · 300-W | normalized error: 5.71 -> 5.65 | Improved |
| replace Chen & Yuille CNN+graphical model with DDN | Chen & Yuille · LSP | mean PCK@0.2: 73.4 -> 84.3 | Improved |
| replace Zhang et al. FCN segmentation approach with DDN regression | Zhang et al. · CUB200-2011 | Back PCK@0.10: 85.6 -> 94.0 | Improved |
| replace Zhang et al. FCN segmentation approach with DDN regression | Zhang et al. · CUB200-2011 | Bee PCK@0.10: 94.9 -> 82.5 | Hurt |
Closest papers by meaning
- Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization (TPAMI 2019 · similarity 0.89)
- Disentangling 3D Pose in a Dendritic CNN for Unconstrained 2D Face Alignment (CVPR 2018 · similarity 0.87)
- Learning To Detect Scene Landmarks for Camera Localization (CVPR 2022 · similarity 0.87)
- Hierarchical Binary CNNs for Landmark Localization with Limited Resources (TPAMI 2018 · similarity 0.86)
- Unsupervised Learning of Object Landmarks by Factorized Spatial Embeddings (ICCV 2017 · similarity 0.86)
- Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation (NeurIPS 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.
