DP
David Picard
cs.CVcs.LGcs.AIstat.MLcs.CLcs.IReess.SPcs.ITDeep Learningeess.IV
On Valency
published · living versionsW_ssnhu7t7·v1 · currentpublished
Rethinking Video Autoencoders for Interactive World Models
with Adrien Ramanana Rahary, Yutong Bai, Nicolas Dufour, Patrick Pérez
1 version
Preprints & journals
58 papers in the corpus · 2016–2026Rethinking Video Autoencoders for Interactive World Models2610.30129v1 · Adrien Ramanana Rahary, Yutong Bai, Nicolas Dufour et al.2026 · 0 citationsarXivon Valency
Dino Forcing Flow Models: Do not denoise what you can predict2610.11751v1 · Arijit Ghosh, Lucas Degeorge, Paul Couairon et al.2026 · 0 citationsarXiv
HuLiGen: Human LiDAR Generation from Parametric Body Models2610.10196v1 · Salma Galaaoui, Nermin Samet, David Picard2026 · 0 citationsarXiv
Diffusable Latents from Structure-Agnostic Distillation2609.39657v1 · Adrien Ramanana Rahary, Nicolas Dufour, Patrick P'erez et al.2026 · 0 citationsarXiv
Balancing Frequencies and Pixels in Flow Matching2609.02748v2 · Lucas Degeorge, Paul Couairon, Arijit Ghosh et al.2026 · 0 citationsarXiv
Random Process Flow Matching: Generative Implicit Representations of Multivariate Random Fields2605.28625v1 · Julien Lalanne, David Picard, Lionel Boillot et al.2026 · 0 citations43rd International Conference on Machine Learning, 2026
PoM: A Linear-Time Replacement for Attention with the Polynomial Mixer2604.06129v1 · David Picard, Nicolas Dufour, Lucas Degeorge et al.2026 · 0 citationsarXiv
One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation2603.23488v3 · Adrien Ramanana Rahary, Nicolas Dufour, Patrick Perez et al.2026 · 0 citationsarXiv
Polynomial Mixing for Efficient Self-supervised Speech Encoders2603.00683v1 · Eva Feillet, Ryan Whetten, David Picard et al.2026 · 0 citationsarXiv
MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency2510.25897v2 · Nicolas Dufour, Lucas Degeorge, Arijit Ghosh et al.2025 · 0 citationsarXiv
3D Human Pose and Shape Estimation from LiDAR Point Clouds: A Review2509.12197v2 · Salma Galaaoui, Eduardo Valle, David Picard et al.2025 · 0 citationsarXiv
Closing the Performance Gap in Generative Recommenders with Collaborative Tokenization and Efficient Modeling2508.14910v1 · Simon Lepage, Jeremie Mary, David Picard2025 · 0 citationsarXiv
How far can we go with ImageNet for Text-to-Image generation?2502.21318v4 · L. Degeorge, A. Ghosh, N. Dufour et al.2025 · 0 citationsarXiv
Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation2412.06781v1 · Nicolas Dufour, David Picard, Vicky Kalogeiton et al.2024 · 6 citationsarXiv
PoM: Efficient Image and Video Generation with the Polynomial Mixer2411.12663v1 · David Picard, Nicolas Dufour2024 · 0 citationsarXiv
PAFUSE: Part-based Diffusion for 3D Whole-Body Pose Estimation2407.10220v2 · Nermin Samet, C'edric Rommel, David Picard et al.2024 · 2 citationsarXiv
Don't drop your samples! Coherence-aware training benefits Conditional diffusion2405.20324v2 · Nicolas Dufour, Victor Besnier, Vicky Kalogeiton et al.2024 · 4 citationsarXiv
Analysis of Classifier-Free Guidance Weight Schedulers2404.13040v2 · Xi Wang, Nicolas Dufour, Nefeli Andreou et al.2024 · 0 citationsTransactions on Machine Learning Research, 2835-8856, 2024
Multiple Locally Linear Kernel Machines2401.09629v1 · David Picard2024 · 1 citationarXiv
Image Compression using only Attention based Neural Networks2310.11265v1 · Natacha Luka, Romain Negrel, David Picard2023 · 0 citationsarXiv
An Analysis of Initial Training Strategies for Exemplar-Free Class-Incremental Learning2308.11677v2 · Gr'egoire Petit, Michael Soumm, Eva Feillet et al.2023 · 10 citationsarXiv
LRVS-Fashion: Extending Visual Search with Referring Instructions2306.02928v3 · Simon Lepage, J'er'emie Mary, David Picard2023 · 0 citationsarXiv
Alphazzle: Jigsaw Puzzle Solver with Deep Monte-Carlo Tree Search2302.00384v1 · Marie-Morgane Paumard, Hedi Tabia, David Picard2023 · 2 citationsarXiv
Towards Unsupervised Visual Reasoning: Do Off-The-Shelf Features Know How to Reason?2212.10292v1 · Monika Wysocza'nska, Tom Monnier, Tomasz Trzci'nski et al.2022 · 0 citationsarXiv
H3WB: Human3.6M 3D WholeBody Dataset and Benchmark2211.15692v2 · Yue Zhu, Nermin Samet, David Picard2022 · 23 citationsarXiv
FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning2211.13131v2 · Gr'egoire Petit, Adrian Popescu, Hugo Schindler et al.2022 · 178 citationsarXiv
SCAM! Transferring humans between images with Semantic Cross Attention Modulation2210.04883v1 · Nicolas Dufour, David Picard, Vicky Kalogeiton2022 · 13 citationsarXiv
Decanus to Legatus: Synthetic training for 2D-3D human pose lifting2210.02231v1 · Yue Zhu, David Picard2022 · 3 citationsarXiv
PlaStIL: Plastic and Stable Memory-Free Class-Incremental Learning2209.06606v2 · Gr'egoire Petit, Adrian Popescu, Eden Belouadah et al.2022 · 1 citationarXiv
Unveiling the Latent Space Geometry of Push-Forward Generative Models2207.10541v3 · Thibaut Issenhuth, Ugo Tanielian, J'er'emie Mary et al.2022 · 0 citationsarXiv
Instance-Aware Observer Network for Out-of-Distribution Object Segmentation2207.08782v3 · Victor Besnier, Andrei Bursuc, David Picard et al.2022 · 1 citationarXiv
EdiBERT, a generative model for image editing2111.15264v3 · Thibaut Issenhuth, Ugo Tanielian, J'er'emie Mary et al.2021 · 2 citationsarXiv
Non asymptotic bounds in asynchronous sum-weight gossip protocols2111.10248v1 · David Picard, J'erome Fellus, St'ephane Garnier2021 · 0 citationsarXiv
Latent reweighting, an almost free improvement for GANs2110.09803v1 · Thibaut Issenhuth, Ugo Tanielian, David Picard et al.2021 · 2 citationsarXiv
Torch.manual_seed(3407) is all you need: On the influence of random seeds in deep learning architectures for computer vision2109.08203v2 · David Picard2021 · 44 citationsarXiv
Image Collation: Matching illustrations in manuscripts2108.08109v1 · Ryad Kaoua, Xi Shen, Alexandra Durr et al.2021 · 5 citationsarXiv
Triggering Failures: Out-Of-Distribution detection by learning from local adversarial attacks in Semantic Segmentation2108.01634v1 · Victor Besnier, Andrei Bursuc, David Picard et al.2021 · 44 citationsarXiv
Multi-Task Deep Learning for Real-Time 3D Human Pose Estimation and Action Recognition.32091993 · Luvizon, Diogo C, Picard, David, Tabia, Hedi2021 · 148 citationsIEEE transactions on pattern analysis and machine intelligence. 2021;43(8):2752-2764
Learning Uncertainty For Safety-Oriented Semantic Segmentation In Autonomous Driving2105.13688v1 · Victor Besnier, David Picard, Alexandre Briot2021 · 12 citationsarXiv
Deep Learning Based Detection for Spectrally Efficient FDM Systems2103.11409v1 · David Picard, Arsenia Chorti2021 · 1 citationarXiv
Rate Analysis and Deep Neural Network Detectors for SEFDM FTN Systems2103.02306v1 · Arsenia Chorti, David Picard2021 · 2 citationsarXiv
SSP-Net: Scalable Sequential Pyramid Networks for Real-Time 3D Human Pose Regression2009.01998v1 · Diogo Luvizon, Hedi Tabia, David Picard2020 · 18 citationsarXiv
Improving Deep Metric Learning with Virtual Classes and Examples Mining2006.06611v1 · Pierre Jacob, David Picard, Aymeric Histace et al.2020 · 1 citationarXiv
DIABLO: Dictionary-based Attention Block for Deep Metric Learning2004.14644v1 · Pierre Jacob, David Picard, Aymeric Histace et al.2020 · 1 citationarXiv
Deepzzle: Solving Visual Jigsaw Puzzles with Deep Learning and Shortest Path Optimization.31944956 · Paumard, Marie-Morgane, Picard, David, Tabia, Hedi2024 · 70 citationsIEEE transactions on image processing : a publication of the IEEE Signal Processing Society. 2020
Consensus-based Optimization for 3D Human Pose Estimation in Camera Coordinates1911.09245v3 · Diogo C Luvizon, Hedi Tabia, David Picard2019 · 33 citationsarXiv
Metric Learning With HORDE: High-Order Regularizer for Deep Embeddings1908.02735v1 · Pierre Jacob, David Picard, Aymeric Histace et al.2019 · 68 citationsarXiv
Efficient Codebook and Factorization for Second Order Representation Learning1906.01972v1 · Pierre Jacob, David Picard, Aymeric Histace et al.2019 · 5 citationsarXiv
Image Reassembly Combining Deep Learning and Shortest Path Problem1809.00898v1 · M.-M. Paumard, D. Picard, H. Tabia2018 · 34 citationsarXiv
Jigsaw Puzzle Solving Using Local Feature Co-Occurrences in Deep Neural Networks1807.03155v1 · Marie-Morgane Paumard, David Picard, Hedi Tabia2018 · 30 citationsarXiv
Career total: 159 works. 58 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.