Dirichlet Splatting: Differentiable Rendering for Wave-Based Inverse Problems
Open Access
- 9 November 2026
- journal article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 45 (6) , 1-19
Abstract
We present Dirichlet Splatting , a physically grounded differentiable rendering method for inverse problems with wave-based coherent sensors. Unlike optical cameras, these sensors observe a scene in a band-limited Fourier space whose continuous point response is complex-valued and oscillatory. Our key observation is that the point spread function of a reflector in this Fourier space is the Dirichlet kernel , not a Gaussian. We instantiate each splat as a Dirichlet kernel in closed form, model each primitive as a planar surfel rendered through a surfel-aware Dirichlet splat whose complex amplitude is set by wave propagation physics, and introduce a sliding Frank-Wolfe adaptation tailored to the rugged, non-convex landscape that the Dirichlet oscillation induces. On terahertz tomography, Dirichlet Splatting recovers reflector geometry with an order of magnitude fewer parameters, faster convergence, and higher accuracy than 3D Gaussian Splatting.Keywords
Funding Information
- NSF (2403124)
- NSF (2408393)
- NSF (2238839)
- NSF (2341952)
This publication has 35 references indexed in Scilit:
- Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction2024
- Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis2024
- Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields2022
- NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis2020
- Seeing Around Street Corners: Non-Line-of-Sight Detection and Tracking In-the-Wild Using Doppler Radar2020
- The sliding Frank–Wolfe algorithm and its application to super-resolution microscopyInverse Problems, 2019
- Variable projection for nonlinear least squares problemsComputational Optimization and Applications, 2012
- Inverse problems in spaces of measuresESAIM: Control, Optimisation and Calculus of Variations, 2012
- Feature-enhanced synthetic aperture radar image formation based on nonquadratic regularizationIEEE Transactions on Image Processing, 2001
- ESPRIT-estimation of signal parameters via rotational invariance techniquesIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989