Valentina Musat — accepted AI-conference papers

2024

NeuralFloors: Conditional Street-Level Scene Generation From BEV Semantic Maps via Neural Fields

Valentina Musat, Daniele De Martini, Matthew Gadd, Paul Newman

RA-L 2024

Semantic Bird's Eye View (BEV) representations are a popular format, being easily interpretable and editable. However, synthesising ground-view images from BEVs is a difficult task as the system would need to learn both the mapping from BEV to Front View (FV) structure as well as to synthesise highl

Cited by 2 Source ↗Scholar ↗

2022

Depth-SIMS: Semi-Parametric Image and Depth Synthesis

Valentina Musat, Daniele De Martini, Matthew Gadd, Paul Newman

ICRA 2022poster

In this paper we present a compositing image synthesis method that generates RGB canvases with well aligned segmentation maps and sparse depth maps, coupled with an in-painting network that transforms the RGB canvases into high quality RGB images and the sparse depth maps into pixel-wise dense depth…

Cited by 8 Source ↗Scholar ↗