References & Further Reading

References

J. J. Park, P. Florence, J. Straub, R. Newcombe, and S. Lovegrove, DeepSDF: learning continuous signed distance functions for shape representation, 2019
Introduced neural SDFs: parameterising the signed distance function as an MLP with an auto-decoder framework. The foundation for all neural implicit geometry methods in this chapter.
Y. Lu and G. Caire, GeRaF: geometry estimation from RF using implicit representations, 2024
The key paper for this chapter. Introduced SDF-based geometry reconstruction from mmWave radar via differentiable matched-filter power rendering.
A. Gropp, L. Yariv, N. Haim, M. Atzmon, and Y. Lipman, Implicit geometric regularization for learning shapes, 2020
Showed that Eikonal regularisation alone (without ground-truth distance labels) suffices to learn valid SDFs from raw point clouds. The theoretical foundation for self-supervised SDF training in GeRaF.
L. Mescheder, M. Oechsle, M. Niemeyer, S. Nowozin, and A. Geiger, Occupancy networks: learning 3D reconstruction in function space, 2019
Introduced occupancy networks for 3D reconstruction. The binary classification alternative to SDFs discussed in Section 25.3.
J. C. Hart, Sphere tracing: a geometric method for the antialiased ray tracing of implicit surfaces, 1996
Introduced sphere tracing for efficient ray-surface intersection with implicit surfaces. The algorithm is used in GeRaF and other SDF-based rendering methods.
P. Wang, L. Liu, Y. Liu, C. Theobalt, T. Komura, and W. Wang, NeuS: learning neural implicit surfaces by volume rendering for multi-view reconstruction, 2021
Combined neural SDFs with volume rendering for high-quality multi-view surface reconstruction. Addressed the challenge of learning SDFs from images without 3D supervision.
B. Mildenhall, P. P. Srinivasan, M. Tancik, J. T. Barron, R. Ramamoorthi, and R. Ng, NeRF: representing scenes as neural radiance fields for view synthesis, 2020
The foundational NeRF paper. Introduced positional encoding and differentiable volume rendering. GeRaF adapts NeRF's principles from optical to radar imaging.
M. Atzmon and Y. Lipman, SAL: sign agnostic learning of shapes from raw data, 2020
Introduced sign-agnostic learning for neural SDFs, handling the sign ambiguity when training from unoriented point clouds.
C. A. Balanis, Advanced Engineering Electromagnetics, Wiley, 2nd ed., 2012
Standard reference for electromagnetic wave propagation, Fresnel coefficients, and material properties at microwave frequencies.
J. A. Sethian, A fast marching level set method for monotonically advancing fronts, 1996
Introduced the fast marching method for solving the Eikonal equation on grids. The computational geometry precursor to neural SDF methods.
T. Mueller, A. Evans, C. Schied, and A. Keller, Instant neural graphics primitives with a multiresolution hash encoding, 2022
Replaced the slow MLP positional encoding with a multi-resolution hash table, reducing neural implicit training from hours to seconds. Applicable to both NeRF and SDF representations.
G. Caire, On the illumination and sensing model for RF imaging, 2026
Caire's unified framework connecting diffraction tomography and MIMO radar models through a common forward model. The theoretical foundation for all RF imaging chapters in this book.