Florian Chabot

Rémi Marsal, Florian Chabot, Angelique Loesch et al.

Self-supervised monocular depth estimation methods aim to be used in critical applications such as autonomous vehicles for environment analysis. To circumvent the potential imperfections of these approaches, a quantification of the prediction confidence is crucial to guide decision-making systems that rely on depth estimation. In this paper, we propose MonoProb, a new unsupervised monocular depth estimation method that returns an interpretable uncertainty, which means that the uncertainty reflects the expected error of the network in its depth predictions. We rethink the stereo or the structure-from-motion paradigms used to train unsupervised monocular depth models as a probabilistic problem. Within a single forward pass inference, this model provides a depth prediction and a measure of its confidence, without increasing the inference time. We then improve the performance on depth and uncertainty with a novel self-distillation loss for which a student is supervised by a pseudo ground truth that is a probability distribution on depth output by a teacher. To quantify the performance of our models we design new metrics that, unlike traditional ones, measure the absolute performance of uncertainty predictions. Our experiments highlight enhancements achieved by our method on standard depth and uncertainty metrics as well as on our tailored metrics. https://github.com/CEA-LIST/MonoProb

Sandra Kara, Hejer Ammar, Florian Chabot et al.

Unsupervised object discovery aims to localize objects in images, while removing the dependence on annotations required by most deep learning-based methods. To address this problem, we propose a fully unsupervised, bottom-up approach, for multiple objects discovery. The proposed approach is a two-stage framework. First, instances of object parts are segmented by using the intra-image similarity between self-supervised local features. The second step merges and filters the object parts to form complete object instances. The latter is performed by two CNN models that capture semantic information on objects from the entire dataset. We demonstrate that the pseudo-labels generated by our method provide a better precision-recall trade-off than existing single and multiple objects discovery methods. In particular, we provide state-of-the-art results for both unsupervised class-agnostic object detection and unsupervised image segmentation.

Jaonary Rabarisoa, Valentin Belissen, Florian Chabot et al.

We present a new self-supervised pre-training of Vision Transformers for dense prediction tasks. It is based on a contrastive loss across views that compares pixel-level representations to global image representations. This strategy produces better local features suitable for dense prediction tasks as opposed to contrastive pre-training based on global image representation only. Furthermore, our approach does not suffer from a reduced batch size since the number of negative examples needed in the contrastive loss is in the order of the number of local features. We demonstrate the effectiveness of our pre-training strategy on two dense prediction tasks: semantic segmentation and monocular depth estimation.

Florian Chabot, Nicolas Granger, Guillaume Lapouge

The Bird's-eye View (BeV) representation is widely used for 3D perception from multi-view camera images. It allows to merge features from different cameras into a common space, providing a unified representation of the 3D scene. The key component is the view transformer, which transforms image views into the BeV. However, actual view transformer methods based on geometry or cross-attention do not provide a sufficiently detailed representation of the scene, as they use a sub-sampling of the 3D space that is non-optimal for modeling the fine structures of the environment. In this paper, we propose GaussianBeV, a novel method for transforming image features to BeV by finely representing the scene using a set of 3D gaussians located and oriented in 3D space. This representation is then splattered to produce the BeV feature map by adapting recent advances in 3D representation rendering based on gaussian splatting. GaussianBeV is the first approach to use this 3D gaussian modeling and 3D scene rendering process online, i.e. without optimizing it on a specific scene and directly integrated into a single stage model for BeV scene understanding. Experiments show that the proposed representation is highly effective and place GaussianBeV as the new state-of-the-art on the BeV semantic segmentation task on the nuScenes dataset.

Sandra Kara, Hejer Ammar, Florian Chabot et al.

Recent works have shown that objects discovery can largely benefit from the inherent motion information in video data. However, these methods lack a proper background processing, resulting in an over-segmentation of the non-object regions into random segments. This is a critical limitation given the unsupervised setting, where object segments and noise are not distinguishable. To address this limitation we propose BMOD, a Background-aware Motion-guided Objects Discovery method. Concretely, we leverage masks of moving objects extracted from optical flow and design a learning mechanism to extend them to the true foreground composed of both moving and static objects. The background, a complementary concept of the learned foreground class, is then isolated in the object discovery process. This enables a joint learning of the objects discovery task and the object/non-object separation. The conducted experiments on synthetic and real-world datasets show that integrating our background handling with various cutting-edge methods brings each time a considerable improvement. Specifically, we improve the objects discovery performance with a large margin, while establishing a strong baseline for object/non-object separation.

Saad Lahlali, Sandra Kara, Hejer Ammar et al.

Object discovery, which refers to the task of localizing objects without human annotations, has gained significant attention in 2D image analysis. However, despite this growing interest, it remains under-explored in 3D data, where approaches rely exclusively on 3D motion, despite its several challenges. In this paper, we present a novel framework that leverages advances in 2D object discovery which are based on 2D motion to exploit the advantages of such motion cues being more flexible and generalizable and to bridge the gap between 2D and 3D modalities. Our primary contributions are twofold: (i) we introduce DIOD-3D, the first baseline for multi-object discovery in 3D data using 2D motion, incorporating scene completion as an auxiliary task to enable dense object localization from sparse input data; (ii) we develop xMOD, a cross-modal training framework that integrates 2D and 3D data while always using 2D motion cues. xMOD employs a teacher-student training paradigm across the two modalities to mitigate confirmation bias by leveraging the domain gap. During inference, the model supports both RGB-only and point cloud-only inputs. Additionally, we propose a late-fusion technique tailored to our pipeline that further enhances performance when both modalities are available at inference. We evaluate our approach extensively on synthetic (TRIP-PD) and challenging real-world datasets (KITTI and Waymo). Notably, our approach yields a substantial performance improvement compared with the 2D object discovery state-of-the-art on all datasets with gains ranging from +8.7 to +15.1 in F1@50 score. The code is available at https://github.com/CEA-LIST/xMOD

Doriand Petit, Steve Bourgeois, Vincent Gay-Bellile et al.

3D semantic segmentation provides high-level scene understanding for applications in robotics, autonomous systems, \textit{etc}. Traditional methods adapt exclusively to either task-specific goals (open-vocabulary segmentation) or scene content (unsupervised semantic segmentation). We propose DiSCO-3D, the first method addressing the broader problem of 3D Open-Vocabulary Sub-concepts Discovery, which aims to provide a 3D semantic segmentation that adapts to both the scene and user queries. We build DiSCO-3D on Neural Fields representations, combining unsupervised segmentation with weak open-vocabulary guidance. Our evaluations demonstrate that DiSCO-3D achieves effective performance in Open-Vocabulary Sub-concepts Discovery and exhibits state-of-the-art results in the edge cases of both open-vocabulary and unsupervised segmentation.

Doriand Petit, Steve Bourgeois, Dumitru Pavel et al.

Recent advances in Neural Fields mostly rely on developing task-specific supervision which often complicates the models. Rather than developing hard-to-combine and specific modules, another approach generally overlooked is to directly inject generic priors on the scene representation (also called inductive biases) into the NeRF architecture. Based on this idea, we propose the RING-NeRF architecture which includes two inductive biases : a continuous multi-scale representation of the scene and an invariance of the decoder's latent space over spatial and scale domains. We also design a single reconstruction process that takes advantage of those inductive biases and experimentally demonstrates on-par performances in terms of quality with dedicated architecture on multiple tasks (anti-aliasing, few view reconstruction, SDF reconstruction without scene-specific initialization) while being more efficient. Moreover, RING-NeRF has the distinctive ability to dynamically increase the resolution of the model, opening the way to adaptive reconstruction.

Doriand Petit, Steve Bourgeois, Vincent Gay-Bellile et al.

Developing a multi-modal language model capable of understanding 3D scenes remains challenging due to the limited availability of 3D training data, in contrast to the abundance of 2D datasets used for vision-language models (VLM). As an alternative, we introduce LLaVA$^3$ (pronounced LLaVA-Cube), a novel method that improves the 3D scene understanding capabilities of VLM using only multi-view 2D images and without any fine-tuning. Inspired by Cubist painters, who represented multiple viewpoints of a 3D object within a single picture, we propose to describe the 3D scene for the VLM through omnidirectional visual representations of each object. These representations are derived from an intermediate multi-view 3D reconstruction of the scene. Extensive experiments on 3D VQA and 3D language grounding show that our approach outperforms previous 2D-based VLM solutions.

Nikolaos Karaliolios, Hervé Le Borgne, Florian Chabot

Semi-Supervised Learning (SSL) seeks to leverage large amounts of non-annotated data along with the smallest amount possible of annotated data in order to achieve the same level of performance as if all data were annotated. A fruitful method in SSL is Pseudo-Labeling (PL), which, however, suffers from the important drawback that the associated loss function has discontinuities in its derivatives, which cause instabilities in performance when labels are very scarce. In the present work, we address this drawback with the introduction of a Smooth Pseudo-Labeling (SP L) loss function. It consists in adding a multiplicative factor in the loss function that smooths out the discontinuities in the derivative due to thresholding. In our experiments, we test our improvements on FixMatch and show that it significantly improves the performance in the regime of scarce labels, without addition of any modules, hyperparameters, or computational overhead. In the more stable regime of abundant labels, performance remains at the same level. Robustness with respect to variation of hyperparameters and training parameters is also significantly improved. Moreover, we introduce a new benchmark, where labeled images are selected randomly from the whole dataset, without imposing representation of each class proportional to its frequency in the dataset. We see that the smooth version of FixMatch does appear to perform better than the original, non-smooth implementation. However, more importantly, we notice that both implementations do not necessarily see their performance improve when labeled images are added, an important issue in the design of SSL algorithms that should be addressed so that Active Learning algorithms become more reliable and explainable.

Abdallah Benzine, Florian Chabot, Bertrand Luvison et al.

Recently, several deep learning models have been proposed for 3D human pose estimation. Nevertheless, most of these approaches only focus on the single-person case or estimate 3D pose of a few people at high resolution. Furthermore, many applications such as autonomous driving or crowd analysis require pose estimation of a large number of people possibly at low-resolution. In this work, we present PandaNet (Pose estimAtioN and Dectection Anchor-based Network), a new single-shot, anchor-based and multi-person 3D pose estimation approach. The proposed model performs bounding box detection and, for each detected person, 2D and 3D pose regression into a single forward pass. It does not need any post-processing to regroup joints since the network predicts a full 3D pose for each bounding box and allows the pose estimation of a possibly large number of people at low resolution. To manage people overlapping, we introduce a Pose-Aware Anchor Selection strategy. Moreover, as imbalance exists between different people sizes in the image, and joints coordinates have different uncertainties depending on these sizes, we propose a method to automatically optimize weights associated to different people scales and joints for efficient training. PandaNet surpasses previous single-shot methods on several challenging datasets: a multi-person urban virtual but very realistic dataset (JTA Dataset), and two real world 3D multi-person datasets (CMU Panoptic and MuPoTS-3D).

Florian Chabot, Quoc-Cuong Pham, Mohamed Chaouch

Real-time single-stage object detectors based on deep learning still remain less accurate than more complex ones. The trade-off between model performance and computational speed is a major challenge. In this paper, we propose a new way to efficiently learn a single-shot detector which offers a very good compromise between these two objectives. To this end, we introduce LapNet, an anchor based detector, trained end-to-end without any sampling strategy. Our approach aims to overcome two important problems encountered in training an anchor based detector: (1) ambiguity in the assignment of anchor to ground truth and (2) class and object size imbalance. To address the first limitation, we propose a soft positive/negative anchor assignment procedure based on a new overlapping function called "Per-Object Normalized Overlap" (PONO). This soft assignment can be self-corrected by the network itself to avoid ambiguity between close objects. To cope with the second limitation, we propose to learn additional weights, that are not used at inference, to efficiently manage sample imbalance. These two contributions make the detector learning more generic whatever the training dataset. Various experiments show the effectiveness of the proposed approach.

Florian Chabot, Mohamed Chaouch, Jaonary Rabarisoa et al.

In this paper, we present a novel approach, called Deep MANTA (Deep Many-Tasks), for many-task vehicle analysis from a given image. A robust convolutional network is introduced for simultaneous vehicle detection, part localization, visibility characterization and 3D dimension estimation. Its architecture is based on a new coarse-to-fine object proposal that boosts the vehicle detection. Moreover, the Deep MANTA network is able to localize vehicle parts even if these parts are not visible. In the inference, the network's outputs are used by a real time robust pose estimation algorithm for fine orientation estimation and 3D vehicle localization. We show in experiments that our method outperforms monocular state-of-the-art approaches on vehicle detection, orientation and 3D location tasks on the very challenging KITTI benchmark.