Research map / 3D vision / Face and shape
Domain-Adaptive Single-View 3D Reconstruction
Pedro O. Pinheiro, Negar Rostamzadeh, Sungjin Ahn
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 shape prior loss and image domain-confusion loss to reconstruction loss (ablation) | DAREC-vox · Pix3D chair (voxel) | Chamfer distance: .220 -> .140 | Improved |
| add shape prior and domain-confusion losses (ablation) | DAREC-pc · Pix3D chair (point cloud) | Chamfer distance: .148 -> .112 | Improved |
| add shape prior loss alone (ablation) | DAREC-vox · Pix3D chair (voxel) | Chamfer distance: .220 -> .196 | Improved |
| add shape prior loss alone (ablation) | DAREC-pc · Pix3D chair (point cloud) | Chamfer distance: .148 -> .140 | Improved |
| add image domain-confusion loss alone (ablation) | DAREC-vox · Pix3D chair (voxel) | Chamfer distance: .220 -> .156 | Improved |
| add image domain-confusion loss alone (ablation) | DAREC-pc · Pix3D chair (point cloud) | Chamfer distance: .148 -> .129 | Improved |
| add shape prior loss on top of domain confusion (ablation) | DAREC-vox · Pix3D chair (voxel) | Chamfer distance: .156 -> .140 | Improved |
| add shape prior loss on top of domain confusion (ablation) | DAREC-pc · Pix3D chair (point cloud) | Chamfer distance: .129 -> .112 | 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.
- MarrNet — MarrNet: 3D Shape Reconstruction via 2.5D Sketches (NeurIPS 2017) · 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 Shape Priors for Single-View 3D Completion and Reconstruction (ECCV 2018 · similarity 0.90)
- Learning View Priors for Single-View 3D Reconstruction (CVPR 2019 · similarity 0.89)
- Shape-Pose Ambiguity in Learning 3D Reconstruction from Images (AAAI 2021 · similarity 0.89)
- Real3D: Towards Scaling Large Reconstruction Models with Real Images (ICCV 2025 · similarity 0.89)
- Planes vs. Chairs: Category-Guided 3D Shape Learning without Any 3D Cues (ECCV 2022 · similarity 0.89)
- MarrNet: 3D Shape Reconstruction via 2.5D Sketches (NeurIPS 2017 · 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.
