Skip to yearly menu bar Skip to main content


Multi-Level Neural Scene Graphs for Dynamic Urban Environments

Tobias Fischer · Lorenzo Porzi · Samuel Rota Bulò · Marc Pollefeys · Peter Kontschieder

Arch 4A-E Poster #153
[ ]
Fri 21 Jun 10:30 a.m. PDT — noon PDT


We estimate the radiance field of large-scale dynamic areas from multiple vehicle captures under varying environmental conditions. Previous works in this domain are either restricted to static environments, do not scale to more than a single short video, or struggle to separately represent dynamic object instances. To this end, we present a novel, decomposable radiance field approach for dynamic urban environments. We propose a multi-level neural scene graph representation that scales to thousands of images from dozens of sequences with hundreds of fast-moving objects. To enable efficient training and rendering of our representation, we develop a fast composite ray sampling and rendering scheme. To test our approach in urban driving scenarios, we introduce a new, novel view synthesis benchmark. We show that our approach outperforms prior art by a significant margin on both established and our proposed benchmark while being faster in training and rendering.

Live content is unavailable. Log in and register to view live content