# AV-Surf: Surface-Enhanced Geometry-Aware Novel-View Acoustic Synthesis

arXiv: https://arxiv.org/abs/2503.12806 · HTML: https://mlsanity.com/paper/2503.12806/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 52 references that are in the map.
- First posted on arXiv 17 Mar 2025.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Gaussian Error Linear Units (GELUs)](https://mlsanity.com/paper/1606.08415/) (2016)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [Nerfstudio: A Modular Framework for Neural Radiance Field Development](https://mlsanity.com/paper/2302.04264/) (2023)
- [Gaussian Opacity Fields: Efficient Adaptive Surface Reconstruction in Unbounded Scenes](https://mlsanity.com/paper/2404.10772/) (2024)
- [NeuMesh: Learning Disentangled Neural Mesh-based Implicit Field for Geometry and Texture Editing](https://mlsanity.com/paper/2207.11911/) (2022)
- [Improving neural implicit surfaces geometry with patch warping](https://mlsanity.com/paper/2112.09648/) (2021)
- [RaDe-GS: Rasterizing Depth in Gaussian Splatting](https://mlsanity.com/paper/2406.01467/) (2024)
- [Self-Supervised Generation of Spatial Audio for 360 Video](https://mlsanity.com/paper/1809.02587/) (2018)
- [Learning Neural Acoustic Fields](https://mlsanity.com/paper/2204.00628/) (2022)
- [AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis](https://mlsanity.com/paper/2302.02088/) (2023)
- [Visually Informed Binaural Audio Generation without Binaural Audios](https://mlsanity.com/paper/2104.06162/) (2021)
- [BinauralGrad: A Two-Stage Conditional Diffusion Probabilistic Model for Binaural Audio Synthesis](https://mlsanity.com/paper/2205.14807/) (2022)
- [Novel-View Acoustic Synthesis](https://mlsanity.com/paper/2301.08730/) (2023)
- [AV-RIR: Audio-Visual Room Impulse Response Estimation](https://mlsanity.com/paper/2312.00834/) (2023)
- [AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis](https://mlsanity.com/paper/2406.08920/) (2024)
- [Listen2Scene: Interactive material-aware binaural sound propagation for reconstructed 3D scenes](https://mlsanity.com/paper/2302.02809/) (2023)
- [CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image](https://mlsanity.com/paper/2412.12906/) (2024)
- [Novel-View Acoustic Synthesis from 3D Reconstructed Rooms](https://mlsanity.com/paper/2310.15130/) (2023)

## Abstract (arXiv)

Accurately modeling sound propagation with complex real-world environments is essential for Novel View Acoustic Synthesis (NVAS). While previous studies have leveraged visual perception to estimate spatial acoustics, the combined use of surface normal and structural details from 3D representations in acoustic modeling has been underexplored. Given their direct impact on sound wave reflections and propagation, surface normals should be jointly modeled with structural details to achieve accurate spatial acoustics. In this paper, we propose a surface-enhanced geometry-aware approach for NVAS to improve spatial acoustic modeling. To achieve this, we exploit geometric priors, such as image, depth map, surface normals, and point clouds obtained using a 3D Gaussian Splatting (3DGS) based framework. We introduce a dual cross-attention-based transformer integrating geometrical constraints into frequency query to understand the surroundings of the emitter. Additionally, we design a ConvNeXt-based spectral features processing network called Spectral Refinement Network (SRN) to synthesize realistic binaural audio. Experimental results on the RWAVS and SoundSpace datasets highlight the necessity of our approach, as it surpasses existing methods in novel view acoustic synthesis.