# RIR-Former: Coordinate-Guided Transformer for Continuous Reconstruction of Room Impulse Responses

arXiv: https://arxiv.org/abs/2602.01861 · HTML: https://mlsanity.com/paper/2602.01861/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 31 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 10 of 10)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Pyroomacoustics: A Python package for audio room simulations and array processing algorithms](https://mlsanity.com/paper/1710.04196/) (2017)
- [Learning Neural Acoustic Fields](https://mlsanity.com/paper/2204.00628/) (2022)
- [Room impulse response reconstruction with physics-informed deep learning](https://mlsanity.com/paper/2401.01206/) (2024)
- [Generative Data Augmentation Challenge: Synthesis of Room Acoustics for Speaker Distance Estimation](https://mlsanity.com/paper/2501.13250/) (2025)
- [Reconstruction of Sound Field through Diffusion Models](https://mlsanity.com/paper/2312.08821/) (2023)
- [Acoustic Reflector Localization: Novel Image Source Reversion and Direct Localization Methods](https://mlsanity.com/paper/1610.05653/) (2016)
- [DiffusionRIR: Room Impulse Response Interpolation using Diffusion Models](https://mlsanity.com/paper/2504.20625/) (2025)
- [Kernel Interpolation of Incident Sound Field in Region Including Scattering Objects](https://mlsanity.com/paper/2309.05634/) (2023)
- [Low-Rank Adaptation of Deep Prior Neural Networks For Room Impulse Response Reconstruction](https://mlsanity.com/paper/2507.09806/) (2025)

## Built on by (most cited first, 2 of 2)

- [HRIR-Former: Grid-Free Time-Domain Reconstruction of Head-Related Impulse Responses with a Spatially Encoded Transformer](https://mlsanity.com/paper/2603.27998/) (2026)
- [PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulation](https://mlsanity.com/paper/2607.23293/) (2026)

## Abstract (arXiv)

Room impulse responses (RIRs) are essential for many acoustic signal processing tasks, yet measuring them densely across space is often impractical. In this work, we propose RIR-Former, a grid-free, one-step feed-forward model for RIR reconstruction. By introducing a sinusoidal encoding module into a transformer backbone, our method effectively incorporates microphone position information, enabling interpolation at arbitrary array locations. Furthermore, a segmented multi-branch decoder is designed to separately handle early reflections and late reverberation, improving reconstruction across the entire RIR. Experiments on diverse simulated acoustic environments demonstrate that RIR-Former consistently outperforms state-of-the-art baselines in terms of normalized mean square error (NMSE) and cosine distance (CD), under varying missing rates and array configurations. These results highlight the potential of our approach for practical deployment and motivate future work on scaling from randomly spaced linear arrays to complex array geometries, dynamic acoustic scenes, and real-world environments.