no code implementations • 4 Dec 2023 • Anh-Quan Cao, Angela Dai, Raoul de Charette
We propose the task of Panoptic Scene Completion (PSC) which extends the recently popular Semantic Scene Completion (SSC) task with instance-level information to produce a richer understanding of the 3D scene.
1 code implementation • 29 Nov 2023 • Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
Generalization to new domains not seen during training is one of the long-standing goals and challenges in deploying neural networks in real-world applications.
no code implementations • 28 Nov 2023 • Ivan Lopes, Fabio Pizzati, Raoul de Charette
In this paper, we propose a method to extract physically-based rendering (PBR) materials from a single real-world image.
no code implementations • 3 Oct 2023 • Weihao Xia, Raoul de Charette, Cengiz Öztireli, Jing-Hao Xue
In this work we present DREAM, an fMRI-to-image method for reconstructing viewed images from brain activities, grounded on fundamental knowledge of the human visual system.
1 code implementation • ICCV 2023 • Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
In this paper, we propose the task of 'Prompt-driven Zero-shot Domain Adaptation', where we adapt a model trained on a source domain using only a general description in natural language of the target domain, i. e., a prompt.
1 code implementation • 6 Dec 2022 • Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
In this paper, we propose the task of `Prompt-driven Zero-shot Domain Adaptation', where we adapt a model trained on a source domain using only a general description in natural language of the target domain, i. e., a prompt.
1 code implementation • ICCV 2023 • Anh-Quan Cao, Raoul de Charette
3D reconstruction from a single 2D image was extensively covered in the literature but relies on depth supervision at training time, which limits its applicability.
1 code implementation • 4 Oct 2022 • Rong Li, Anh-Quan Cao, Raoul de Charette
Annotation of large-scale 3D data is notoriously cumbersome and costly.
Ranked #1 on Weakly supervised Semantic Segmentation on nuScenes
1 code implementation • 17 Jun 2022 • Ivan Lopes, Tuan-Hung Vu, Raoul de Charette
Multi-task learning has recently become a promising solution for a comprehensive understanding of complex scenes.
Ranked #94 on Semantic Segmentation on NYU Depth v2
1 code implementation • CVPR 2022 • Anh-Quan Cao, Raoul de Charette
MonoScene proposes a 3D Semantic Scene Completion (SSC) framework, where the dense geometry and semantics of a scene are inferred from a single monocular RGB image.
1 code implementation • 26 Nov 2021 • Fabio Pizzati, Jean-François Lalonde, Raoul de Charette
To enforce feature consistency, our framework learns a style manifold between source and proxy anchor domains (assumed to be composed of large numbers of images).
no code implementations • 9 Sep 2021 • Anthony Dell'Eva, Fabio Pizzati, Massimo Bertozzi, Raoul de Charette
Our comprehensive evaluation setting shows we are able to generate realistic translations, with minimal priors, and training only on a few images.
1 code implementation • 29 Jul 2021 • Fabio Pizzati, Pietro Cerri, Raoul de Charette
Image-to-image translation (i2i) networks suffer from entanglement effects in presence of physics-related phenomena in target domain (such as occlusions, fog, etc), lowering altogether the translation quality, controllability and variability.
no code implementations • 16 Mar 2021 • Pranav Agarwal, Pierre de Beaucorps, Raoul de Charette
Deep reinforcement Learning for end-to-end driving is limited by the need of complex reward engineering.
no code implementations • 12 Mar 2021 • Luis Roldao, Raoul de Charette, Anne Verroust-Blondet
Semantic Scene Completion (SSC) aims to jointly estimate the complete geometry and semantics of a scene, assuming partial sparse input.
Ranked #9 on 3D Semantic Scene Completion on NYUv2
2 code implementations • CVPR 2021 • Fabio Pizzati, Pietro Cerri, Raoul de Charette
CoMoGAN is a continuous GAN relying on the unsupervised reorganization of the target data on a functional manifold.
3 code implementations • 18 Jan 2021 • Maximilian Jaritz, Tuan-Hung Vu, Raoul de Charette, Émilie Wirbel, Patrick Pérez
Domain adaptation is an important task to enable learning when labels are scarce.
no code implementations • 6 Sep 2020 • Maxime Tremblay, Shirsendu Sukanta Halder, Raoul de Charette, Jean-François Lalonde
In this context, we present a rain rendering pipeline that enables the systematic evaluation of common computer vision algorithms to controlled amounts of rain.
2 code implementations • 24 Aug 2020 • Luis Roldão, Raoul de Charette, Anne Verroust-Blondet
We introduce a new approach for multiscale 3Dsemantic scene completion from voxelized sparse 3D LiDAR scans.
Ranked #4 on 3D Semantic Scene Completion on KITTI-360
1 code implementation • 9 Jun 2020 • Etienne Dubeau, Mathieu Garon, Benoit Debaque, Raoul de Charette, Jean-François Lalonde
In this paper, we propose, for the first time, to use an event-based camera to increase the speed of 3D object tracking in 6 degrees of freedom.
no code implementations • ECCV 2020 • Fabio Pizzati, Pietro Cerri, Raoul de Charette
Image-to-image translation is affected by entanglement phenomena, which may occur in case of target data encompassing occlusions such as raindrops, dirt, etc.
1 code implementation • CVPR 2020 • Maximilian Jaritz, Tuan-Hung Vu, Raoul de Charette, Émilie Wirbel, Patrick Pérez
In this work, we explore how to learn from multi-modality and propose cross-modal UDA (xMUDA) where we assume the presence of 2D images and 3D point clouds for 3D semantic segmentation.
no code implementations • 23 Oct 2019 • Fabio Pizzati, Raoul de Charette, Michela Zaccaria, Pietro Cerri
Image-to-image translation architectures may have limited effectiveness in some circumstances.
no code implementations • ICCV 2019 • Shirsendu Sukanta Halder, Jean-François Lalonde, Raoul de Charette
Our rendering relies on a physical particle simulator, an estimation of the scene lighting and an accurate rain photometric modeling to augment images with arbitrary amount of realistic rain or fog.
no code implementations • 5 Aug 2019 • Raoul de Charette, Sotiris Manitsaris
We reconstruct 3D deformable object through time, in the context of a live pottery making process where the crafter molds the object.
no code implementations • 25 Jun 2019 • Luis Roldão, Raoul de Charette, Anne Verroust-Blondet
To achieve fully autonomous navigation, vehicles need to compute an accurate model of their direct surrounding.
no code implementations • 2 Aug 2018 • Maximilian Jaritz, Raoul de Charette, Emilie Wirbel, Xavier Perrotton, Fawzi Nashashibi
Convolutional neural networks are designed for dense data, but vision data is often sparse (stereo depth, point clouds, pen stroke, etc.).
Ranked #9 on Depth Completion on KITTI Depth Completion
no code implementations • 6 Jul 2018 • Maximilian Jaritz, Raoul de Charette, Marin Toromanoff, Etienne Perot, Fawzi Nashashibi
We present research using the latest reinforcement learning algorithm for end-to-end driving without any mediated perception (object recognition, scene understanding).