Stefanie Walz

Papers

Total Citations

H-Index

About

Stefanie Walz is a researcher whose work sits at the intersection of neural scene representation, sensor fusion, and robust perception for autonomous systems. Her research focuses on enabling machines to reliably interpret their environments under challenging real-world conditions, with a particular emphasis on adverse weather and multimodal sensing. Walz's most recognized contribution, "ScatterNeRF: Seeing Through Fog with Physically-Based Inverse Neural Rendering" (2023, 25 citations), tackles one of autonomous driving's most persistent challenges: visual degradation caused by fog, rain, and snow. By integrating physically-based scattering models into neural radiance field frameworks, her work offers a principled approach to recovering clean scene representations from corrupted imagery — a critical capability for safe deployment of autonomous vehicles and drones. Her follow-up work on "Radar Fields" (2024, 11 citations) extends neural field methods to FMCW radar data, addressing a significant gap in multimodal scene reconstruction. Radar's resilience to adverse weather makes this contribution especially compelling, complementing her broader research vision of all-weather, all-sensor perception. Together, these contributions position Walz as an emerging voice in robust, physics-informed perception research, with work directly relevant to the safety-critical demands of autonomous navigation.