Research map / 3D vision / Human pose estimation
ClearPose: Large-Scale Transparent Object Dataset and Benchmark
Xiaotong Chen, Huijie Zhang, Zeren Yu, Anthony Opipari, Odest Chadwicke Jenkins
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 TransCG instead of ImplicitDepth | depth completion · ClearPose New Background | RMSE: 0.07 -> 0.03 | Improved |
| use TransCG instead of ImplicitDepth | depth completion · ClearPose Filled Liquid | RMSE: 0.14 -> 0.04 | Improved |
| use TransCG instead of ImplicitDepth | depth completion · ClearPose Translucent Cover | RMSE: 0.16 -> 0.16 | No clear effect |
| train FFB6D on ground-truth depth rather than raw depth, test on raw | FFB6D · ClearPose New Background | Accuracy: 44.264 -> 59.694 | Improved |
| train FFB6D on ground truth, test on TransCG-completed depth instead of GT depth | FFB6D · ClearPose New Background | Accuracy: 59.694 -> 49.517 | Hurt |
| test on completed depth instead of raw depth (train GT) | FFB6D · ClearPose New Background | Accuracy: 44.264 -> 49.517 | Improved |
| use Xu et al. instead of FFB6D (raw) | pose estimation · ClearPose Opaque Distractor | Accuracy: 0.4618 -> 42.630 | Improved |
| use Xu et al. instead of FFB6D (raw) | pose estimation · ClearPose Filled Liquid | Accuracy: 7.6908 -> 34.500 | Improved |
| change test scene from New Background to Heavy Occlusion | FFB6D (train/test GT) · ClearPose | Accuracy: 59.694 -> 26.331 | Hurt |
| change test scene from New Background to Translucent Cover | TransCG · ClearPose depth completion | RMSE: 0.03 -> 0.16 | Hurt |
Closest papers by meaning
- KeyPose: Multi-View 3D Labeling and Keypoint Estimation for Transparent Objects (CVPR 2020 · similarity 0.88)
- RGB-D Local Implicit Function for Depth Completion of Transparent Objects (CVPR 2021 · similarity 0.88)
- Seeing and Seeing Through the Glass: Real and Synthetic Data for Multi-Layer Depth Estimation (ICCV 2025 · similarity 0.87)
- Cubify Anything: Scaling Indoor 3D Object Detection (CVPR 2025 · similarity 0.86)
- A Simple yet Universal Framework for Depth Completion (NeurIPS 2024 · similarity 0.85)
- Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data (CVPR 2024 · similarity 0.85)
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.
