Research map / 3D vision / Face and shape
Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images
Jiahui Lei, Srinath Sridhar, Paul Guerrero, Minhyuk Sung, Niloy Mitra, Leonidas J. Guibas
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 a UV amplifier MLP before the surface branch (ablation) | Pix2Surf · ShapeNetPlain chair | reconstruction error: 10.37 -> 2.61 | Improved |
| add pretraining of the NOCS-UV branch with NOCS map supervision (ablation) | Pix2Surf · ShapeNetPlain chair | reconstruction error: 3.64 -> 2.61 | Improved |
| use learned UV chart instead of image coordinates as chart (ablation) | Pix2Surf · ShapeNetPlain single-view | reconstruction error: 2.90 -> 1.73 | Improved |
| use learned UV chart instead of image coordinates as chart (ablation) | Pix2Surf · ShapeNetPlain single-view | discontinuity score: 0.40 -> 0.59 | Improved |
| add multi-view feature pooling and consistency loss (5 views vs single view) (ablation) | Pix2Surf · ShapeNetPlain | reconstruction error: 1.73 -> 1.52 | Improved |
| add multi-view feature pooling and consistency loss (5 views vs single view) (ablation) | Pix2Surf · ShapeNetPlain | consistency error: 9.65 -> 8.38 | Improved |
| add multi-view feature pooling and consistency loss (5 views vs single view) (ablation) | Pix2Surf · ShapeNetPlain | discontinuity score: 0.59 -> 0.58 | No clear effect |
| replace X-NOCS point cloud output with continuous parametric surface | Pix2Surf · ShapeNetPlain single-view | reconstruction error: 2.43 -> 1.73 | Improved |
| replace fixed AtlasNet layout with learned chart | Pix2Surf · ShapeNetPlain chair | reconstruction error: 3.36 -> 1.91 | Improved |
| replace AtlasNet with Pix2Surf on car | Pix2Surf · ShapeNetPlain car, single-view | reconstruction error: 1.54 -> 1.67 | Hurt |
| add joint hidden surface prediction (ablation) | Pix2Surf · ShapeNetPlain visible surface | reconstruction error: 1.73 -> 1.78 | No clear effect |
| use Pix2Surf instead of X-NOCS for hidden surfaces | Pix2Surf · ShapeNetPlain hidden surface | hidden error: 2.48 -> 1.92 | 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.
- Pixel2Mesh++ — Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images (ECCV 2018) · 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
- SurfNet: Generating 3D Shape Surfaces Using Deep Residual Networks (CVPR 2017 · similarity 0.91)
- A Papier-Mâché Approach to Learning 3D Surface Generation (CVPR 2018 · similarity 0.90)
- Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling (CVPR 2018 · similarity 0.88)
- Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images Using a View-Based Representation (IJCV 2020 · similarity 0.88)
- Front2Back: Single View 3D Shape Reconstruction via Front to Back Prediction (CVPR 2020 · similarity 0.88)
- Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering (ECCV 2024 · 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.
