Research map / Image generation / GANs
SurfaceNet: Adversarial SVBRDF Estimation From a Single Image
Giuseppe Vecchio, Simone Palazzo, Concetto Spampinato
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 learnable upsampling decoder to the base generator (ablation) | SurfaceNet generator · Synthetic SVBRDF (flash) | rendering RMSE: 0.185 -> 0.087 | Improved |
| add skip connections with downsampled input after decoder (ablation) | SurfaceNet generator · Synthetic SVBRDF (flash) | rendering RMSE: 0.087 -> 0.073 | Improved |
| add skip connections (ablation) | SurfaceNet generator · Synthetic SVBRDF (flash) | normal RMSE: 0.093 -> 0.122 | Hurt |
| add image-level discriminator with adversarial loss (ablation) | SurfaceNet generator · Synthetic SVBRDF (flash) | rendering RMSE: 0.073 -> 0.067 | Improved |
| use patch-based instead of image-based discriminator (ablation) | SurfaceNet · Synthetic SVBRDF (flash) | rendering RMSE: 0.067 -> 0.058 | Improved |
| use patch discriminator instead of image discriminator (ablation) | SurfaceNet · Synthetic SVBRDF (flash) | roughness RMSE: 0.065 -> 0.029 | Improved |
| add MS-SSIM to L1 supervised loss (ablation) | SurfaceNet · Synthetic SVBRDF (flash) | rendering RMSE: 0.134 -> 0.088 | Improved |
| add adversarial loss to supervised loss (ablation) | SurfaceNet · Synthetic SVBRDF (flash) | rendering RMSE: 0.088 -> 0.058 | Improved |
| use adversarial loss alone instead of full loss (ablation) | SurfaceNet · Synthetic SVBRDF (flash) | diffuse RMSE: 0.017 -> 0.133 | Hurt |
| include unlabeled real images in training (ablation) | SurfaceNet · Synthetic SVBRDF (flash) | rendering RMSE: 0.058 -> 0.064 | Hurt |
| include unlabeled real images in training (ablation) | SurfaceNet · Synthetic SVBRDF (flash) | roughness RMSE: 0.029 -> 0.043 | Hurt |
| include unlabeled real images in training (ablation) | SurfaceNet · Real photographs | qualitative SVBRDF quality | Improved |
Closest papers by meaning
- A Lightweight Approach for On-The-Fly Reflectance Estimation (ICCV 2017 · similarity 0.89)
- Materials for Masses: SVBRDF Acquisition with a Single Mobile Phone Image (ECCV 2018 · similarity 0.87)
- Invertible Neural BRDF for Object Inverse Rendering (ECCV 2020 · similarity 0.87)
- Deep Photometric Stereo Networks for Determining Surface Normal and Reflectances (TPAMI 2020 · similarity 0.86)
- Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance (CVPR 2024 · similarity 0.86)
- Material Palette: Extraction of Materials from a Single Image (CVPR 2024 · similarity 0.85)
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.
