4 papers
R3DPA: Leveraging 3D Representation Alignment and RGB Pretrained Priors for LiDAR Scene Generation
Nicolas Sereyjol-Garros, Ellington Kirby, Victor Besnier +1
LiDAR scene synthesis is an emerging solution to scarcity in 3D data for robotic tasks such as autonomous driving. Recent approaches employ diffusion or flow matching models to gen…
Test-Time Conditioning with Representation-Aligned Visual Features
Nicolas Sereyjol-Garros, Ellington Kirby, Victor Letzelter +2
While representation alignment with self-supervised models has been shown to improve diffusion model training, its potential for enhancing inference-time conditioning remains large…
Driving on Registers
Ellington Kirby, Alexandre Boulch, Yihong Xu +11
We present DrivoR, a simple and efficient transformer-based architecture for end-to-end autonomous driving. Our approach builds on pretrained Vision Transformers (ViTs) and introdu…
LOGen: Toward Lidar Object Generation by Point Diffusion
Ellington Kirby, Mickael Chen, Renaud Marlet +1
The generation of LiDAR scans is a growing topic with diverse applications to autonomous driving. However, scan generation remains challenging, especially when compared to the rapi…