Research map / 3D vision / Face and shape
SASNet: Spatially-Adaptive Sinusoidal Networks for INRs
Haoan Feng, Diana Aldana, Tiago Novello, Leila De Floriani
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 SASNet instead of FINER | SIREN-style INR · Kodak | PSNR: 37.72 -> 40.43 | Improved |
| use SASNet instead of FINER | SIREN-style INR · Kodak | PSNR_edge: 34.67 -> 38.12 | Improved |
| add spatially-adaptive masks over SIREN fixed frequency embedding (ablation) | SASNet · SDF reconstruction (Armadillo) | error map | Improved |
| add spatially-adaptive masks to frequency embedding layer (ablation) | SASNet · image fitting | background noise | Improved |
| use SASNet instead of SIREN | SIREN · CT medical images | PSNR: 47.07 -> 50.21 | Improved |
| use SASNet instead of FINER | FINER · CT medical images | PSNR_edge: 45.56 -> 49.58 | Improved |
| use SASNet instead of FINER | FINER · FFHQ | PSNR: 38.16 -> 39.69 | Improved |
| use SASNet instead of FINER | FINER · FFHQ | noisiness: 4.975 -> 4.278 | Improved |
| use SASNet instead of SIREN | SIREN · 2D image fitting | average step time (us): 29,224 -> 43,107 | Hurt |
| use SASNet instead of SIREN | SIREN · 3D shape fitting | average step time: 17,557 -> 22,175 | Hurt |
| use SASNet instead of SIREN | SIREN · 2D image fitting | time to same training loss (minutes): 58 -> 10 | Improved |
| vary omega_0 for SASNet (ablation) | SASNet · image fitting | PSNR | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 on most shared results.
- FINER — FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions (CVPR 2024) · better on 6 of 6 shared results
- NeuRBF — NeuRBF: A Neural Fields Representation with Adaptive Radial Basis Functions (ICCV 2023) · better on 3 of 3 shared results
- GaussianImage — GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting (ECCV 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks (CVPR 2025 · similarity 0.86)
- FreSh: Frequency Shifting for Accelerated Neural Representation Learning (ICLR 2025 · similarity 0.85)
- End-to-End Implicit Neural Representations for Classification (CVPR 2025 · similarity 0.85)
- VI^3NR: Variance Informed Initialization for Implicit Neural Representations (CVPR 2025 · similarity 0.85)
- FINER: Flexible Spectral-bias Tuning in Implicit NEural Representation by Variable-periodic Activation Functions (CVPR 2024 · similarity 0.84)
- Learning Spatially Collaged Fourier Bases for Implicit Neural Representation (AAAI 2024 · similarity 0.84)
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.
