Research map / 3D vision / Face and shape
RenderNet: A deep convolutional network for differentiable rendering from 3D shapes
Thu H Nguyen-Phuoc, Chuan Li, Stephen Balaban, Yongliang Yang
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 |
|---|---|---|---|
| Use RenderNet to render Phong-shaded images instead of the EC encoder-decoder | Phong-shaded chair rendering · ShapeNet chairs | PSNR | Improved |
| Use RenderNet rather than the fully connected EC architecture | Rendering objects of unseen categories · Unseen object categories | generalization | Improved |
| Optimize shape through a pretrained 3D autoencoder prior instead of optimizing the shape directly (ablation) | RenderNet image-based reconstruction · Single-image shape reconstruction | reconstruction quality | Improved |
| Add the shape prior to the reconstruction optimization (ablation) | RenderNet image-based reconstruction · Single-image shape reconstruction | Intersection-over-Union | Improved |
Closest papers by meaning
- Soft Rasterizer: A Differentiable Renderer for Image-Based 3D Reasoning (ICCV 2019 · similarity 0.90)
- A General Differentiable Mesh Renderer for Image-Based 3D Reasoning (TPAMI 2020 · similarity 0.89)
- Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering (ICLR 2021 · similarity 0.89)
- Visual Object Networks: Image Generation with Disentangled 3D Representations (NeurIPS 2018 · similarity 0.89)
- Pixel2Mesh++: 3D Mesh Generation and Refinement From Multi-View Images (TPAMI 2022 · similarity 0.88)
- Global Latent Neural Rendering (CVPR 2024 · similarity 0.86)
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.
