Research map / 3D vision / 3D generation
3D Appearance Super-Resolution With Deep Learning
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 |
|---|---|---|---|
| Fine-tune EDSR on the 3D texture domain (ablation) | EDSR · 3DASR average ×2 | PSNR: 18.89 -> 23.66 | Helped |
| Add LR normal maps to the fine-tuned network (ablation) | EDSR-FT · 3DASR average ×2 | PSNR: 23.66 -> 23.85 | Helped |
| Add HR rather than LR normal maps (ablation) | NLR · 3DASR average ×2 | PSNR: 23.85 -> 26.46 | Helped |
| Use more varied whole-dataset training data rather than subset-specific training (ablation) | NLR-Sub · 3DASR average ×2 | PSNR: 23.75 -> 23.85 | Helped |
| Use NHR instead of HRST | 3DASR · ETH3D and SyB3R versus Collection and MiddleBury | PSNR | Mixed |
| Use bilinear rather than bicubic interpolation | Interpolation baselines · 3DASR average ×2 | PSNR: 22.28 -> 22.67 | Helped |
Closest papers by meaning
- MNSRNet: Multimodal Transformer Network for 3D Surface Super-Resolution (CVPR 2022 · similarity 0.88)
- Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation (NeurIPS 2018 · similarity 0.88)
- Sequence Matters: Harnessing Video Models in 3D Super-Resolution (AAAI 2025 · similarity 0.86)
- SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration (CVPR 2024 · similarity 0.85)
- Multi-view Reconstruction via SfM-guided Monocular Depth Estimation (CVPR 2025 · similarity 0.85)
- What You See is What You GAN: Rendering Every Pixel for High-Fidelity Geometry in 3D GANs (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.