Research map / 3D vision / Face and shape
Synthesizing 3D Shapes From Silhouette Image Collections Using Multi-Projection Generative Adversarial Networks
Check 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 |
|---|---|---|---|
| increase the number of projections and discriminators (ablation) | MP-GAN · Synthetic chairs | FID: 79.61 -> 29.45 | Helped |
| increase projections from 16 to 24 (ablation) | MP-GAN · Synthetic chairs | FID: 32.45 -> 29.45 | Helped |
| increase the number of view clusters (ablation) | VP-MP-GAN · Synthetic chairs | FID: 79.61 -> 33.95 | Helped |
| increase view clusters from 8 to 24 (ablation) | VP-MP-GAN · Synthetic chairs | FID: 34.32 -> 33.95 | Helped |
| iteratively alternate GAN and view-predictor training (ablation) | VP-MP-GAN · Synthetic chairs | view classification accuracy: 42.7% -> 75.6% | Helped |
| increase the number of view clusters (ablation) | VP-MP-GAN · Synthetic chairs | view classification accuracy: 42.7% -> 75.6% | Helped |
Closest papers by meaning
- Synthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes With Deep Generative Networks (CVPR 2017 · similarity 0.89)
- Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (NeurIPS 2016 · similarity 0.89)
- 3D generation on ImageNet (ICLR 2023 · similarity 0.88)
- Do 2D GANs Know 3D Shape? Unsupervised 3D Shape Reconstruction from 2D Image GANs (ICLR 2021 · similarity 0.88)
- Visual Object Networks: Image Generation with Disentangled 3D Representations (NeurIPS 2018 · similarity 0.88)
- What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs (CVPR 2024 · similarity 0.87)
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.