Research map / 3D vision / Face and shape
Learning Generative Neural Networks for 3D Colorization
Zhenpei Yang, Lihang Liu, Qixing Huang
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 |
|---|---|---|---|
| replace with conditional WGAN baseline | 3D colorization generative model · User study: quality | % ranked best: 79% -> 6% | Hurt |
| replace with conditional WGAN baseline | 3D colorization generative model · User study: diversity | % ranked best: 73% -> 15% | Hurt |
| use two-channel classification loss instead of single 10-class loss (ablation) | classification loss · Testing error | reconstruction error | Improved |
| use classification loss instead of regression loss (ablation) | classification loss · Testing error | reconstruction error | Improved |
| remove the encoder and mask decoder output with input shape (ablation) | generative network · ShapeNet colorization | training | Hurt |
| naive data term without propagation (Eq. 2) (ablation) | data term · ShapeNet colorization | diversity | Hurt |
Closest papers by meaning
- Learning Representations for Automatic Colorization (ECCV 2016 · similarity 0.88)
- Synthesizing 3D Shapes via Modeling Multi-View Depth Maps and Silhouettes With Deep Generative Networks (CVPR 2017 · similarity 0.88)
- Pixel2Mesh++: 3D Mesh Generation and Refinement From Multi-View Images (TPAMI 2022 · similarity 0.88)
- Color3D: Controllable and Consistent 3D Colorization with Personalized Colorizer (ICLR 2026 · similarity 0.88)
- 3D-PRNN: Generating Shape Primitives With Recurrent Neural Networks (ICCV 2017 · similarity 0.87)
- Inferring 3D Shapes from Image Collections Using Adversarial Networks (IJCV 2020 · 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.
