Research map / 3D vision / Face and shape
Sobolev Training for Implicit Neural Representations with Approximated Image Derivatives
Wentao Yuan, Qingtian Zhu, Xiangyue Liu, Yikang Ding, Haotian Zhang, Chi Zhang
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 Sobolev training (derivative supervision) | SIREN · Set5 image regression | PSNR: 26.22 -> 30.28 | Improved |
| add Sobolev training (derivative supervision) | ReLU+P.E. · Set5 image regression | PSNR: 26.59 -> 28.63 | Improved |
| add Sobolev training | SIREN+P.E. · LLFF inverse rendering | PSNR: 23.38 -> 24.38 | Improved |
| add Sobolev training | ReLU+P.E. · LLFF inverse rendering | SSIM: 0.706 -> 0.708 | No clear effect |
| add Sobolev training | SIREN · Audio regression | PSNR: 35.89 -> 41.23 | Improved |
| use Sobel filter instead of vanilla filter (ablation) | SIREN+S.T. · Set5 image regression | PSNR: 30.24 -> 30.28 | No clear effect |
| use Sobel filter instead of vanilla filter (ablation) | SIREN+P.E.+S.T. · LLFF inverse rendering | PSNR: 24.28 -> 24.38 | No clear effect |
| increase MLP layers from 4 to 8 (ablation) | SIREN+P.E.+S.T. · LLFF inverse rendering | PSNR: 23.66 -> 24.38 | Improved |
| increase MLP layers from 4 to 8 (ablation) | SIREN+P.E. · LLFF inverse rendering | SSIM: 0.654 -> 0.682 | Improved |
| replace ReLU with sine activation under Sobolev training (ablation) | MLP · Set5 image regression | PSNR: 28.63 -> 30.28 | Improved |
| replace ReLU with sine without Sobolev training (ablation) | MLP · Set5 image regression | PSNR: 26.59 -> 26.22 | No clear effect |
| add Sobolev training at 378x504 training resolution | SIREN+P.E. · LLFF inverse rendering | SSIM: 0.750 -> 0.766 | Improved |
Closest papers by meaning
- Implicit Representations via Operator Learning (ICML 2024 · similarity 0.88)
- VI^3NR: Variance Informed Initialization for Implicit Neural Representations (CVPR 2025 · similarity 0.88)
- Learning Transferable Features for Implicit Neural Representations (NeurIPS 2024 · similarity 0.87)
- Implicit Neural Representations and the Algebra of Complex Wavelets (ICLR 2024 · similarity 0.87)
- Nonparametric Teaching of Implicit Neural Representations (ICML 2024 · similarity 0.86)
- MIRE: Matched Implicit Neural Representations (CVPR 2025 · 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.
