# SANDWICH: Towards an Offline, Differentiable, Fully-Trainable Wireless Neural Ray-Tracing Surrogate

arXiv: https://arxiv.org/abs/2411.08767 · HTML: https://mlsanity.com/paper/2411.08767/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 38 references that are in the map.
- First posted on arXiv 13 Nov 2024.

## Builds on (most cited first, 16 of 16)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains](https://mlsanity.com/paper/2006.10739/) (2020)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments](https://mlsanity.com/paper/2205.15967/) (2022)
- [Sionna RT: Differentiable Ray Tracing for Radio Propagation Modeling](https://mlsanity.com/paper/2303.11103/) (2023)
- [NeRF2: Neural Radio-Frequency Radiance Fields](https://mlsanity.com/paper/2305.06118/) (2023)
- [RF-Diffusion: Radio Signal Generation via Time-Frequency Diffusion](https://mlsanity.com/paper/2404.09140/) (2024)
- [Learning Radio Environments by Differentiable Ray Tracing](https://mlsanity.com/paper/2311.18558/) (2023)
- [Rethinking Decision Transformer via Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2311.00267/) (2023)
- [Neural Ray-Tracing: Learning Surfaces and Reflectance for Relighting and View Synthesis](https://mlsanity.com/paper/2104.13562/) (2021)
- [Physics-informed Generalizable Wireless Channel Modeling with Segmentation and Deep Learning: Fundamentals, Methodologies, and Challenges](https://mlsanity.com/paper/2401.01288/) (2024)
- [WiThRay: A Versatile Ray-Tracing Simulator for Smart Wireless Environments](https://mlsanity.com/paper/2304.11385/) (2023)
- [Differentiable and Learnable Wireless Simulation with Geometric Transformers](https://mlsanity.com/paper/2406.14995/) (2024)
- [Integrated Ray-Tracing and Coverage Planning Control using Reinforcement Learning](https://mlsanity.com/paper/2304.09631/) (2023)
- [Towards Practical Cell-Free 6G Network Deployments: An Open-Source End-to-End Ray Tracing Simulator](https://mlsanity.com/paper/2401.08624/) (2023)

## Built on by (most cited first, 1 of 1)

- [Transform-Invariant Generative Ray Path Sampling for Efficient Radio Propagation Modeling](https://mlsanity.com/paper/2603.01655/) (2026)

## Abstract (arXiv)

Wireless ray-tracing (RT) is emerging as a key tool for three-dimensional (3D) wireless channel modeling, driven by advances in graphical rendering. Current approaches struggle to accurately model beyond 5G (B5G) network signaling, which often operates at higher frequencies and is more susceptible to environmental conditions and changes. Existing online learning solutions require real-time environmental supervision during training, which is both costly and incompatible with GPU-based processing. In response, we propose a novel approach that redefines ray trajectory generation as a sequential decision-making problem, leveraging generative models to jointly learn the optical, physical, and signal properties within each designated environment. Our work introduces the Scene-Aware Neural Decision Wireless Channel Raytracing Hierarchy (SANDWICH), an innovative offline, fully differentiable approach that can be trained entirely on GPUs. SANDWICH offers superior performance compared to existing online learning methods, outperforms the baseline by 4e^-2 radian in RT accuracy, and only fades 0.5 dB away from toplined channel gain estimation.