Research map / 3D vision / Depth and stereo
INFER: Learning Implicit Neural Frequency Response Fields for Confined Acoustic Environments
Harshvardhan C. Takawale, Nirupam Roy, C. Phillip Brown
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 spectral loss (ablation) | INFER · Buck | Phase error: 1.44 -> 0.48 | Improved |
| add phase loss (ablation) | INFER · Buck | Phase error: 0.98 -> 0.48 | Improved |
| add Kramers-Kronig loss (ablation) | INFER · Buck | Phase error: 0.77 -> 0.48 | Improved |
| add Kramers-Kronig regularizer (ablation) | INFER · MeshRIR | Phase error: 1.224 -> 1.194 | Improved |
| add energy loss (ablation) | INFER · Buck | T60: 24.0 -> 9.8 | Hurt |
| add spectral loss (ablation) | INFER · Buck | T60: 2.4 -> 9.8 | Hurt |
| train with 75% data instead of 30% (ablation) | INFER · Buck | Phase error: 1.08 -> 0.5 | Improved |
| increase rays from 32x16 to 64x32 (ablation) | INFER · Buck | Amplitude error: 0.43 -> 0.12 | Improved |
| increase points per ray from 40 to 64 (ablation) | INFER · Buck | Phase error: 1.13 -> 0.48 | Improved |
| increase points per ray from 64 to 70 (ablation) | INFER · Buck | Phase error: 0.48 -> 0.48 | No clear effect |
| INFER vs NAF on Tesla | INFER · Tesla | Phase MAE: 1.625 -> 0.590 | Improved |
| INFER vs NAF on Buck T60 | INFER · Buck | T60: 1.3 vs 9.8 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- INRAS — INRAS: Implicit Neural Representation for Audio Scenes (NeurIPS 2022) · better on 8 of 8 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
- Deep Neural Room Acoustics Primitive (ICML 2024 · similarity 0.85)
- Tuning the Frequencies: Robust Training for Sinusoidal Neural Networks (CVPR 2025 · similarity 0.85)
- Resounding Acoustic Fields with Reciprocity (NeurIPS 2025 · similarity 0.85)
- FreSh: Frequency Shifting for Accelerated Neural Representation Learning (ICLR 2025 · similarity 0.85)
- Representing Sounds as Neural Amplitude Fields: A Benchmark of Coordinate-MLPs and a Fourier Kolmogorov-Arnold Framework (AAAI 2025 · similarity 0.84)
- Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark (CVPR 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.
