268 citations · 1.1k across the 40 of their papers we have counts for
45 papers
Butterfly factorization by algorithmic identification of rank-one blocks
Léon Zheng, Gilles Puy, Elisa Riccietti +2
Many matrices associated with fast transforms posess a certain low-rank property characterized by the existence of several block partitionings of the matrix, where each block is of…
You Never Get a Second Chance To Make a Good First Impression: Seeding Active Learning for 3D Semantic Segmentation
Nermin Samet, Oriane Siméoni, Gilles Puy +3
We propose SeedAL, a method to seed active learning for efficient annotation of 3D point clouds for semantic segmentation. Active Learning (AL) iteratively selects relevant data fr…
SALUDA: Surface-based Automotive Lidar Unsupervised Domain Adaptation
Björn Michele, Alexandre Boulch, Gilles Puy +3
Learning models on one labeled dataset that generalize well on another domain is a difficult task, as several shifts might happen between the data domains. This is notably the case…
RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving
Angelika Ando, Spyros Gidaris, Andrei Bursuc +3
Casting semantic segmentation of outdoor LiDAR point clouds as a 2D problem, e.g., via range projection, is an effective and popular approach. These projection-based methods usuall…
Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation
Gilles Puy, Alexandre Boulch, Renaud Marlet
Semantic segmentation of point clouds in autonomous driving datasets requires techniques that can process large numbers of points efficiently. Sparse 3D convolutions have become th…
Unsupervised Object Localization: Observing the Background to Discover Objects
Oriane Siméoni, Chloé Sekkat, Gilles Puy +3
Recent advances in self-supervised visual representation learning have paved the way for unsupervised methods tackling tasks such as object discovery and instance segmentation. How…
ALSO: Automotive Lidar Self-supervision by Occupancy estimation
Alexandre Boulch, Corentin Sautier, Björn Michele +2
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 whi…
Take One Gram of Neural Features, Get Enhanced Group Robustness
Simon Roburin, Charles Corbière, Gilles Puy +4
Predictive performance of machine learning models trained with empirical risk minimization (ERM) can degrade considerably under distribution shifts. The presence of spurious correl…
Self-supervised learning with rotation-invariant kernels
Léon Zheng, Gilles Puy, Elisa Riccietti +2
We introduce a regularization loss based on kernel mean embeddings with rotation-invariant kernels on the hypersphere (also known as dot-product kernels) for self-supervised learni…
Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data
Corentin Sautier, Gilles Puy, Spyros Gidaris +3
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 performi…
NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Dropping
Alexandre Boulch, Pierre-Alain Langlois, Gilles Puy +1
There has been recently a growing interest for implicit shape representations. Contrary to explicit representations, they have no resolution limitations and they easily deal with a…
FacialFilmroll: High-resolution multi-shot video editing
Bharath Bhushan Damodaran, Emmanuel Jolly, Gilles Puy +6
We present FacialFilmroll, a solution for spatially and temporally consistent editing of faces in one or multiple shots. We build upon unwrap mosaic [Rav-Acha et al. 2008] by speci…
PCAM: Product of Cross-Attention Matrices for Rigid Registration of Point Clouds
Anh-Quan Cao, Gilles Puy, Alexandre Boulch +1
Rigid registration of point clouds with partial overlaps is a longstanding problem usually solved in two steps: (a) finding correspondences between the point clouds; (b) filtering…
Localizing Objects with Self-Supervised Transformers and no Labels
Oriane Siméoni, Gilles Puy, Huy V. Vo +6
Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activ…
Generative Zero-Shot Learning for Semantic Segmentation of 3D Point Clouds
Björn Michele, Alexandre Boulch, Gilles Puy +2
While there has been a number of studies on Zero-Shot Learning (ZSL) for 2D images, its application to 3D data is still recent and scarce, with just a few methods limited to classi…
OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning
Spyros Gidaris, Andrei Bursuc, Gilles Puy +3
Learning image representations without human supervision is an important and active research field. Several recent approaches have successfully leveraged the idea of making such a…
FLOT: Scene Flow on Point Clouds Guided by Optimal Transport
Gilles Puy, Alexandre Boulch, Renaud Marlet
We propose and study a method called FLOT that estimates scene flow on point clouds. We start the design of FLOT by noticing that scene flow estimation on point clouds reduces to e…
High Resolution Face Age Editing
Xu Yao, Gilles Puy, Alasdair Newson +2
Face age editing has become a crucial task in film post-production, and is also becoming popular for general purpose photography. Recently, adversarial training has produced some o…
Photo style transfer with consistency losses
Xu Yao, Gilles Puy, Patrick Pérez
We address the problem of style transfer between two photos and propose a new way to preserve photorealism. Using the single pair of photos available as input, we train a pair of d…
FKAConv: Feature-Kernel Alignment for Point Cloud Convolution
Alexandre Boulch, Gilles Puy, Renaud Marlet
Recent state-of-the-art methods for point cloud processing are based on the notion of point convolution, for which several approaches have been proposed. In this paper, inspired by…
Scattering Features for Multimodal Gait Recognition
Srđan Kitić, Gilles Puy, Patrick Pérez +1
We consider the problem of identifying people on the basis of their walk (gait) pattern. Classical approaches to tackle this problem are based on, e.g., video recordings or piezoel…
A Flexible Convolutional Solver with Application to Photorealistic Style Transfer
Gilles Puy, Patrick Pérez
We propose a new flexible deep convolutional neural network (convnet) to perform fast visual style transfer. In contrast to existing convnets that address the same task, our archit…
Structured sampling and fast reconstruction of smooth graph signals
Gilles Puy, Patrick Pérez
This work concerns sampling of smooth signals on arbitrary graphs. We first study a structured sampling strategy for such smooth graph signals that consists of a random selection o…
Unifying local and non-local signal processing with graph CNNs
Gilles Puy, Srdan Kitic, Patrick Pérez
This paper deals with the unification of local and non-local signal processing on graphs within a single convolutional neural network (CNN) framework. Building upon recent works on…