# Non-line-of-sight imaging with arbitrary relay surface geometries via 3D Gaussian Transient Rendering

arXiv: https://arxiv.org/abs/2606.21270 · HTML: https://mlsanity.com/paper/2606.21270/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 61 references that are in the map.
- First posted on arXiv 19 Jun 2026.

## Builds on (most cited first, 25 of 25)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022)
- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023)
- [SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM](https://mlsanity.com/paper/2312.02126/) (2023)
- [Virtual Wave Optics for Non-Line-of-Sight Imaging](https://mlsanity.com/paper/1810.07535/) (2018)
- [Non-line-of-Sight Imaging via Neural Transient Fields](https://mlsanity.com/paper/2101.00373/) (2021)
- [Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar](https://mlsanity.com/paper/1912.06613/) (2019)
- [Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction](https://mlsanity.com/paper/2307.09555/) (2023)
- [Non-Line-of-Sight Reconstruction using Efficient Transient Rendering](https://mlsanity.com/paper/1809.08044/) (2018)
- [Z-Splat: Z-Axis Gaussian Splatting for Camera-Sonar Fusion](https://mlsanity.com/paper/2404.04687/) (2024)
- [Towards 3D Vision with Low-Cost Single-Photon Cameras](https://mlsanity.com/paper/2403.17801/) (2024)
- [RadarSplat: Radar Gaussian Splatting for High-Fidelity Data Synthesis and 3D Reconstruction of Autonomous Driving Scenes](https://mlsanity.com/paper/2506.01379/) (2025)
- [NLOS-NeuS: Non-line-of-sight Neural Implicit Surface](https://mlsanity.com/paper/2303.12280/) (2023)
- [Keyhole Imaging: Non-Line-of-Sight Imaging and Tracking of Moving Objects Along a Single Optical Path](https://mlsanity.com/paper/1912.06727/) (2019)
- [Non-line-of-sight imaging with arbitrary illumination and detection pattern](https://mlsanity.com/paper/2211.00648/) (2022)
- [Blurred LiDAR for Sharper 3D: Robust Handheld 3D Scanning with Diffuse LiDAR and RGB](https://mlsanity.com/paper/2411.19474/) (2024)
- [Differentiable Transient Rendering](https://mlsanity.com/paper/2206.06193/) (2022)
- [Few-shot Non-line-of-sight Imaging with Signal-surface Collaborative Regularization](https://mlsanity.com/paper/2211.15367/) (2022)
- [SonarSplat: Novel View Synthesis of Imaging Sonar via Gaussian Splatting](https://mlsanity.com/paper/2504.00159/) (2025)
- [Omni-Line-of-Sight Imaging for Holistic Shape Reconstruction](https://mlsanity.com/paper/2304.10780/) (2023)
- [Self-Calibrating, Fully Differentiable NLOS Inverse Rendering](https://mlsanity.com/paper/2309.12047/) (2023)
- [Recovering Parametric Scenes from Very Few Time-of-Flight Pixels](https://mlsanity.com/paper/2509.16132/) (2025)
- [Domain Reduction Strategy for Non Line of Sight Imaging](https://mlsanity.com/paper/2308.10269/) (2023)

## Abstract (arXiv)

Imaging objects hidden outside the direct line of sight expands the effective field of view and is critical for applications such as autonomous driving and robotic perception. Despite impressive progress in time-of-flight (ToF)-based non-line-of-sight (NLOS) imaging, real-world deployment remains challenging because practical measurements are often collected over spatially limited, arbitrarily shaped relay regions-conditions that violate the planar-wall and dense-sampling assumptions made by most existing methods. To address these limitations, we propose a LOS-guided NLOS imaging pipeline that imposes no geometric assumptions on the relay surface and naturally supports both confocal and non-confocal configurations. Our method represents the hidden scene using 3D Gaussian primitives and couples them with an efficient, differentiable transient rendering model, enabling end-to-end optimization directly from measured transients. We validate our approach on real-world measurements from both a public dataset and a custom-built capture system. Across settings, our method achieves state-of-the-art reconstruction fidelity under spatially limited, sparsely sampled conditions, and significantly outperforms existing methods on complex, arbitrary relay surface geometries.