Research map / 3D vision / Face and shape
Geometry-Aware Network for Non-Rigid Shape Prediction From a Single View
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 geometry-aware 2D detection, depth estimation, and shape inference instead of direct 3D coordinate regression | DeformNet versus Resnet-50 V2 · Synthetic test, New Text | 3D reconstruction error: 11.23 -> 3.28 | Helped |
| Use geometry-aware 2D detection, depth estimation, and shape inference instead of direct 3D coordinate regression | DeformNet versus Resnet-50 V2 · Synthetic test, No-Text | 3D reconstruction error: 8.39 -> 2.86 | Helped |
| Use geometry-aware 2D detection, depth estimation, and shape inference instead of direct 3D coordinate regression | DeformNet versus Resnet-50 V2 · Synthetic test, New Text with occlusions | 3D reconstruction error: 18.50 -> 4.09 | Helped |
| Use DeformNet rather than the strongest analytic baseline, Ch14IsoLsq-It | Synthetic test, Known Text · Known Text, no occlusion | 3D reconstruction error: 4.85 -> 2.64 | Helped |
| Use DeformNet rather than the strongest analytic baseline, Ch14IsoLsq-It | Synthetic test, New Text · New Text, no occlusion | 3D reconstruction error: 5.3 -> 3.28 | Helped |
| Use DeformNet rather than Resnet-50 V2 | Synthetic test, Known Text · Known Text, no occlusion | 3D reconstruction error: 0.92 -> 2.64 | Hurt |
| Train with noisy and blurred surface boundaries (ablation) | DeformNet · Synthetic reconstruction | 3D reconstruction error | No clear effect |
| Evaluate under synthetic specularities | DeformNet · Synthetic reconstruction with specularities | 3D reconstruction error | No clear effect |
Closest papers by meaning
- SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks (CVPR 2017 · similarity 0.89)
- Learning to Infer Implicit Surfaces without 3D Supervision (NeurIPS 2019 · similarity 0.89)
- Structured Prediction of Unobserved Voxels From a Single Depth Image (CVPR 2016 · similarity 0.89)
- Topologically-Aware Deformation Fields for Single-View 3D Reconstruction (CVPR 2022 · similarity 0.89)
- Pixels, Voxels, and Views: A Study of Shape Representations for Single View 3D Object Shape Prediction (CVPR 2018 · similarity 0.88)
- Unsupervised Learning of Dense Shape Correspondence (CVPR 2019 · similarity 0.88)
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.