Research map / 3D vision / Face and shape
Planes vs. Chairs: Category-Guided 3D Shape Learning without Any 3D Cues
Zixuan Huang, Stefan Stojanov, Anh Thai, Varun Jampani, James M. Rehg
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 category-based shape metric learning (ablation) | MCSV SDF model · ShapeNet-13 | CD: 0.458 -> 0.430 | Improved |
| add category labels (ablation) | MCSV SDF model · ShapeNet-13 | CD: 0.520 -> 0.430 | Improved |
| add viewpoint cycle-consistency regularization (ablation) | MCSV SDF model · ShapeNet-13 | CD: 0.463 -> 0.430 | Improved |
| add adversarial regularization (ablation) | MCSV SDF model · ShapeNet-13 | CD: 0.532 -> 0.430 | Improved |
| add category-based shape metric learning (ablation) | MCSV SDF model · ShapeNet-55 | CD: 0.620 -> 0.541 | Improved |
| add category labels (ablation) | MCSV SDF model · ShapeNet-55 | CD: 0.801 -> 0.541 | Improved |
| add category-based shape metric learning (ablation) | MCSV SDF model · Pascal3D+ | CD: 0.673 -> 0.580 | Improved |
| add category-based shape metric learning (ablation) | MCSV SDF model · Pascal3D+ | F-Score@1.0: 0.1038 -> 0.1139 | Mixed |
| use the proposed method instead of adapted SDF-SRN | SDF-SRN · ShapeNet-13 | CD: 0.682 -> 0.430 | Improved |
| use the proposed method instead of adapted SDF-SRN | SDF-SRN · ShapeNet-55 | CD: 1.172 -> 0.541 | Improved |
| use the proposed method instead of SDF-SRN | SDF-SRN · Pascal3D+ | CD: 0.777 -> 0.580 | Improved |
| use the proposed method instead of Ye et al. | Ye et al. · Pascal3D+ | CD: 0.625 -> 0.580 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- SDF-SRN — SDF-SRN: Learning Signed Distance 3D Object Reconstruction from Static Images (NeurIPS 2020) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Learning Category-Specific Mesh Reconstruction from Image Collections (ECCV 2018 · similarity 0.91)
- Multiview Aggregation for Learning Category-Specific Shape Reconstruction (NeurIPS 2019 · similarity 0.90)
- Weakly-Supervised Learning of Category-Specific 3D Object Shapes (TPAMI 2019 · similarity 0.90)
- Learning Category-Specific 3D Shape Models From Weakly Labeled 2D Images (CVPR 2017 · similarity 0.90)
- Shape-Pose Ambiguity in Learning 3D Reconstruction from Images (AAAI 2021 · similarity 0.90)
- Learning 3D Object Shape and Layout Without 3D Supervision (CVPR 2022 · similarity 0.90)
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.
