Corentin Sautier

Alexandre Boulch, Corentin Sautier, Björn Michele et al.

We propose a new self-supervised method for pre-training the backbone of deep perception models operating on point clouds. The core idea is to train the model on a pretext task which is the reconstruction of the surface on which the 3D points are sampled, and to use the underlying latent vectors as input to the perception head. The intuition is that if the network is able to reconstruct the scene surface, given only sparse input points, then it probably also captures some fragments of semantic information, that can be used to boost an actual perception task. This principle has a very simple formulation, which makes it both easy to implement and widely applicable to a large range of 3D sensors and deep networks performing semantic segmentation or object detection. In fact, it supports a single-stream pipeline, as opposed to most contrastive learning approaches, allowing training on limited resources. We conducted extensive experiments on various autonomous driving datasets, involving very different kinds of lidars, for both semantic segmentation and object detection. The results show the effectiveness of our method to learn useful representations without any annotation, compared to existing approaches. Code is available at https://github.com/valeoai/ALSO

Alexander H. Liu, Alexis Tacnet, Andy Ehrenberg et al. · deepmind, tsinghua

We introduce Voxtral TTS, an expressive multilingual text-to-speech model that generates natural speech from as little as 3 seconds of reference audio. Voxtral TTS adopts a hybrid architecture that combines auto-regressive generation of semantic speech tokens with flow-matching for acoustic tokens. These tokens are encoded and decoded with Voxtral Codec, a speech tokenizer trained from scratch with a hybrid VQ-FSQ quantization scheme. In human evaluations conducted by native speakers, Voxtral TTS is preferred for multilingual voice cloning due to its naturalness and expressivity, achieving a 68.4\% win rate over ElevenLabs Flash v2.5. We release the model weights under a CC BY-NC license.

Gilles Puy, Spyros Gidaris, Alexandre Boulch et al.

Self-supervised image backbones can be used to address complex 2D tasks (e.g., semantic segmentation, object discovery) very efficiently and with little or no downstream supervision. Ideally, 3D backbones for lidar should be able to inherit these properties after distillation of these powerful 2D features. The most recent methods for image-to-lidar distillation on autonomous driving data show promising results, obtained thanks to distillation methods that keep improving. Yet, we still notice a large performance gap when measuring the quality of distilled and fully supervised features by linear probing. In this work, instead of focusing only on the distillation method, we study the effect of three pillars for distillation: the 3D backbone, the pretrained 2D backbones, and the pretraining dataset. In particular, thanks to our scalable distillation method named ScaLR, we show that scaling the 2D and 3D backbones and pretraining on diverse datasets leads to a substantial improvement of the feature quality. This allows us to significantly reduce the gap between the quality of distilled and fully-supervised 3D features, and to improve the robustness of the pretrained backbones to domain gaps and perturbations.

Corentin Sautier, Gilles Puy, Alexandre Boulch et al.

We present a surprisingly simple and efficient method for self-supervision of 3D backbone on automotive Lidar point clouds. We design a contrastive loss between features of Lidar scans captured in the same scene. Several such approaches have been proposed in the literature from PointConstrast, which uses a contrast at the level of points, to the state-of-the-art TARL, which uses a contrast at the level of segments, roughly corresponding to objects. While the former enjoys a great simplicity of implementation, it is surpassed by the latter, which however requires a costly pre-processing. In BEVContrast, we define our contrast at the level of 2D cells in the Bird's Eye View plane. Resulting cell-level representations offer a good trade-off between the point-level representations exploited in PointContrast and segment-level representations exploited in TARL: we retain the simplicity of PointContrast (cell representations are cheap to compute) while surpassing the performance of TARL in downstream semantic segmentation.

Corentin Sautier, Gilles Puy, Alexandre Boulch et al.

Online object segmentation and tracking in Lidar point clouds enables autonomous agents to understand their surroundings and make safe decisions. Unfortunately, manual annotations for these tasks are prohibitively costly. We tackle this problem with the task of class-agnostic unsupervised online instance segmentation and tracking. To that end, we leverage an instance segmentation backbone and propose a new training recipe that enables the online tracking of objects. Our network is trained on pseudo-labels, eliminating the need for manual annotations. We conduct an evaluation using metrics adapted for temporal instance segmentation. Computing these metrics requires temporally-consistent instance labels. When unavailable, we construct these labels using the available 3D bounding boxes and semantic labels in the dataset. We compare our method against strong baselines and demonstrate its superiority across two different outdoor Lidar datasets.

Corentin Sautier, Gilles Puy, Alexandre Boulch et al.

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 typically rely on end-to-end deep learning architectures and extensive manual annotations of instances, the significant cost and time investment required for labeling large-scale point cloud datasets remains a major bottleneck in this field. In this work, we demonstrate that competitive panoptic segmentation can be achieved using only semantic labels, with instances predicted without any training or annotations. Our method outperforms {most} state-of-the-art supervised methods on standard benchmarks including SemanticKITTI and nuScenes, and outperforms every publicly available method on SemanticKITTI as a drop-in instance head replacement, while running in real-time on a single-threaded CPU and requiring no instance labels. It is fully explainable, and requires no learning or parameter tuning. Alpine combined with state-of-the-art semantic segmentation ranks first on the official panoptic segmentation leaderboard of SemanticKITTI. Code is available at https://github.com/valeoai/Alpine/

David Picard, Nicolas Dufour, Lucas Degeorge et al.

This paper introduces the Polynomial Mixer (PoM), a novel token mixing mechanism with linear complexity that serves as a drop-in replacement for self-attention. PoM aggregates input tokens into a compact representation through a learned polynomial function, from which each token retrieves contextual information. We prove that PoM satisfies the contextual mapping property, ensuring that transformers equipped with PoM remain universal sequence-to-sequence approximators. We replace standard self-attention with PoM across five diverse domains: text generation, handwritten text recognition, image generation, 3D modeling, and Earth observation. PoM matches the performance of attention-based models while drastically reducing computational cost when working with long sequences. The code is available at https://github.com/davidpicard/pom.

Arslan Artykov, Corentin Sautier, Vincent Lepetit

Understanding articulated objects is a fundamental challenge in robotics and digital twin creation. To effectively model such objects, it is essential to recover both part segmentation and the underlying joint parameters. Despite the importance of this task, previous work has largely focused on setups like multi-view systems, object scanning, or static cameras. In this paper, we present the first data-driven approach that jointly predicts part segmentation and joint parameters from monocular video captured with a freely moving camera. Trained solely on synthetic data, our method demonstrates strong generalization to real-world objects, offering a scalable and practical solution for articulated object understanding. Our approach operates directly on casually recorded video, making it suitable for real-time applications in dynamic environments. Project webpage: https://aartykov.github.io/sim2art/

Alexander H. Liu, Andy Ehrenberg, Andy Lo et al.

We introduce Voxtral Realtime, a natively streaming automatic speech recognition model that matches offline transcription quality at sub-second latency. Unlike approaches that adapt offline models through chunking or sliding windows, Voxtral Realtime is trained end-to-end for streaming, with explicit alignment between audio and text streams. Our architecture builds on the Delayed Streams Modeling framework, introducing a new causal audio encoder and Ada RMS-Norm for improved delay conditioning. We scale pretraining to a large-scale dataset spanning 13 languages. At a delay of 480ms, Voxtral Realtime achieves performance on par with Whisper, the most widely deployed offline transcription system. We release the model weights under the Apache 2.0 license.

Corentin Sautier, Gilles Puy, Spyros Gidaris et al.

Segmenting or detecting objects in sparse Lidar point clouds are two important tasks in autonomous driving to allow a vehicle to act safely in its 3D environment. The best performing methods in 3D semantic segmentation or object detection rely on a large amount of annotated data. Yet annotating 3D Lidar data for these tasks is tedious and costly. In this context, we propose a self-supervised pre-training method for 3D perception models that is tailored to autonomous driving data. Specifically, we leverage the availability of synchronized and calibrated image and Lidar sensors in autonomous driving setups for distilling self-supervised pre-trained image representations into 3D models. Hence, our method does not require any point cloud nor image annotations. The key ingredient of our method is the use of superpixels which are used to pool 3D point features and 2D pixel features in visually similar regions. We then train a 3D network on the self-supervised task of matching these pooled point features with the corresponding pooled image pixel features. The advantages of contrasting regions obtained by superpixels are that: (1) grouping together pixels and points of visually coherent regions leads to a more meaningful contrastive task that produces features well adapted to 3D semantic segmentation and 3D object detection; (2) all the different regions have the same weight in the contrastive loss regardless of the number of 3D points sampled in these regions; (3) it mitigates the noise produced by incorrect matching of points and pixels due to occlusions between the different sensors. Extensive experiments on autonomous driving datasets demonstrate the ability of our image-to-Lidar distillation strategy to produce 3D representations that transfer well on semantic segmentation and object detection tasks.