A self-supervised diffusion model predicts multimodal drivable corridors as contour points in monocular images, and beats two segmentation baselines on CARLA and nuScenes.
Lift, splat, shoot: Encoding images from arbitrary camera rigs by implicitly un- projecting to 3d,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Diffusion-FS: Multimodal Free-Space Prediction via Diffusion for Autonomous Driving
A self-supervised diffusion model predicts multimodal drivable corridors as contour points in monocular images, and beats two segmentation baselines on CARLA and nuScenes.