Gilles Puy

SSC-Priors: Exploring Semantic and Visibility Priors to Boost Lidar Semantic Scene Completion

Tetiana Martyniuk, Jonathan Seele, Alexandre Boulch +3

This paper investigates easy strategies to boost the performance of existing networks for lidar semantic scene completion (SSC) without requiring complex architectural redesigns. T…

Exploring Easy Boosts for Lidar Semantic Scene Completion

Tetiana Martyniuk, Jonathan Seele, Alexandre Boulch +3

This paper investigates "free lunch" strategies to boost the performance of lidar semantic scene completion (SSC) without requiring complex architectural redesigns. We first demons…

Vanilla ViT for Automotive Point Cloud Semantic Segmentation

Gilles Puy, Nermin Samet, Alexandre Boulch +3

Plain Transformers have become the de-facto architecture for processing text, audio, image, and video, offering a unified backbone for multimodal learning. However, state-of-the-ar…

IGLOSS: Image Generation for Lidar Open-vocabulary Semantic Segmentation

Nermin Samet, Gilles Puy, Renaud Marlet

This paper presents a new method for the zero-shot open-vocabulary semantic segmentation (OVSS) of 3D automotive lidar data. To circumvent the recognized image-text modality gap th…

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…

3D sans 3D Scans: Scalable Pre-training from Video-Generated Point Clouds

Ryousuke Yamada, Kohsuke Ide, Yoshihiro Fukuhara +4

Despite recent progress in 3D self-supervised learning, collecting large-scale 3D scene scans remains expensive and labor-intensive. In this work, we investigate whether 3D represe…

Improving Multimodal Distillation for 3D Semantic Segmentation under Domain Shift

Björn Michele, Alexandre Boulch, Gilles Puy +3

Semantic segmentation networks trained under full supervision for one type of lidar fail to generalize to unseen lidars without intervention. To reduce the performance gap under do…

LiDPM: Rethinking Point Diffusion for Lidar Scene Completion

Tetiana Martyniuk, Gilles Puy, Alexandre Boulch +2

Training diffusion models that work directly on lidar points at the scale of outdoor scenes is challenging due to the difficulty of generating fine-grained details from white noise…

Is clustering enough for LiDAR instance segmentation? A state-of-the-art training-free baseline

Corentin Sautier, Gilles Puy, Alexandre Boulch +2

Panoptic segmentation of LiDAR point clouds is fundamental to outdoor scene understanding, with autonomous driving being a primary application. While state-of-the-art approaches ty…

UNIT: Unsupervised Online Instance Segmentation through Time

Corentin Sautier, Gilles Puy, Alexandre Boulch +2

Online object segmentation and tracking in Lidar point clouds enables autonomous agents to understand their surroundings and make safe decisions. Unfortunately, manual annotations…

Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation

Björn Michele, Alexandre Boulch, Tuan-Hung Vu +3

We tackle the challenging problem of source-free unsupervised domain adaptation (SFUDA) for 3D semantic segmentation. It amounts to performing domain adaptation on an unlabeled tar…

MILAN: Milli-Annotations for Lidar Semantic Segmentation

Nermin Samet, Gilles Puy, Oriane Siméoni +1

Annotating lidar point clouds for autonomous driving is a notoriously expensive and time-consuming task. In this work, we show that the quality of recent self-supervised lidar scan…