119 citations · 156 across the 24 of their papers we have counts for
31 papers
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…
StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets
Anh-Quan Cao, Ivan Lopes, Raoul de Charette
Multi-task learning for dense prediction is limited by the need for extensive annotation for every task, though recent works have explored training with partial task labels. Levera…
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…
FLOSS: Free Lunch in Open-vocabulary Semantic Segmentation
Yasser Benigmim, Mohammad Fahes, Tuan-Hung Vu +2
In this paper, we challenge the conventional practice in Open-Vocabulary Semantic Segmentation (OVSS) of using averaged class-wise text embeddings, which are typically obtained by…
LatteCLIP: Unsupervised CLIP Fine-Tuning via LMM-Synthetic Texts
Anh-Quan Cao, Maximilian Jaritz, Matthieu Guillaumin +2
Large-scale vision-language pre-trained (VLP) models (e.g., CLIP) are renowned for their versatility, as they can be applied to diverse applications in a zero-shot setup. However,…
Domain Adaptation with a Single Vision-Language Embedding
Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc +2
Domain adaptation has been extensively investigated in computer vision but still requires access to target data at the training time, which might be difficult to obtain in real-wor…
CLIP's Visual Embedding Projector is a Few-shot Cornucopia
Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc +2
We introduce ProLIP, a simple and architecture-agnostic method for adapting contrastively pretrained vision-language models, such as CLIP, to few-shot classification. ProLIP fine-t…
UMBRAE: Unified Multimodal Brain Decoding
Weihao Xia, Raoul de Charette, Cengiz Öztireli +1
We address prevailing challenges of the brain-powered research, departing from the observation that the literature hardly recover accurate spatial information and require subject-s…
PaSCo: Urban 3D Panoptic Scene Completion with Uncertainty Awareness
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 u…
Material Palette: Extraction of Materials from a Single Image
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. We do so in two steps: first, we map regions of the image t…
A Simple Recipe for Language-guided Domain Generalized Segmentation
Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc +2
Generalization to new domains not seen during training is one of the long-standing challenges in deploying neural networks in real-world applications. Existing generalization techn…
DREAM: Visual Decoding from Reversing Human Visual System
Weihao Xia, Raoul de Charette, Cengiz Öztireli +1
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. We craf…
PØDA: Prompt-driven Zero-shot Domain Adaptation
Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc +2
Domain adaptation has been vastly investigated in computer vision but still requires access to target images at train time, which might be intractable in some uncommon conditions.…
SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields
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. To relax the de…
COARSE3D: Class-Prototypes for Contrastive Learning in Weakly-Supervised 3D Point Cloud Segmentation
Rong Li, Anh-Quan Cao, Raoul de Charette
Annotation of large-scale 3D data is notoriously cumbersome and costly. As an alternative, weakly-supervised learning alleviates such a need by reducing the annotation by several o…
MonoScene: Monocular 3D Semantic Scene Completion
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. Different from…
ManiFest: Manifold Deformation for Few-shot Image Translation
Fabio Pizzati, Jean-François Lalonde, Raoul de Charette
Most image-to-image translation methods require a large number of training images, which restricts their applicability. We instead propose ManiFest: a framework for few-shot image…
Physics-informed Guided Disentanglement in Generative Networks
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 altoge…
Goal-constrained Sparse Reinforcement Learning for End-to-End Driving
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. Sparse rewards can circumvent this challenge but suffers from long training…
CoMoGAN: continuous model-guided image-to-image translation
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. To that matter, we introduce a new Functional Instance Normaliza…
Rain rendering for evaluating and improving robustness to bad weather
Maxime Tremblay, Shirsendu Sukanta Halder, Raoul de Charette +1
Rain fills the atmosphere with water particles, which breaks the common assumption that light travels unaltered from the scene to the camera. While it is well-known that rain affec…
RGB-D-E: Event Camera Calibration for Fast 6-DOF Object Tracking
Etienne Dubeau, Mathieu Garon, Benoit Debaque +2
Augmented reality devices require multiple sensors to perform various tasks such as localization and tracking. Currently, popular cameras are mostly frame-based (e.g. RGB and Depth…
Model-based occlusion disentanglement for image-to-image translation
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. Our unsupervised mode…
xMUDA: Cross-Modal Unsupervised Domain Adaptation for 3D Semantic Segmentation
Maximilian Jaritz, Tuan-Hung Vu, Raoul de Charette +2
Unsupervised Domain Adaptation (UDA) is crucial to tackle the lack of annotations in a new domain. There are many multi-modal datasets, but most UDA approaches are uni-modal. In th…