GINA-3D: Learning to Generate Implicit Neural Assets in the Wild

In-the-Wild Driving Data "Same kind…" "Similar size…" GINA-3D Synthesis Composition with Background NeRF GINA-3D Reconstruction "Night time…" In-the-wild Driving Data "Random…" Figure 1. Leveraging in-the-wild data for generative assets modeling embodies a scalable approach for simulation. GINA-3D uses real-world driving data to perform various synthesis tasks for realistic 3D implicit neural assets. Left: Multi-sensor observations in the wild. Middle: Asset reconstruction and conditional synthesis. Right: Scene composition with background neural fields [1].