Thomas Lucas — accepted AI-conference papers

2025

DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers

Mert Bülent Sarıyıldız, Philippe Weinzaepfel, Thomas Lucas, Pau de Jorge, Diane Larlus, Yannis Kalantidis

CVPR 2025poster

Recent multi-teacher distillation methods have unified the encoders of multiple foundation models into a single encoder, achieving competitive performance on core vision tasks like classification, segmentation, and depth estimation. This led us to ask: Could similar success be achieved when the pool…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Cross-view and Cross-pose Completion for 3D Human Understanding

Matthieu Armando, Salma Galaaoui, Fabien Baradel, Thomas Lucas, Vincent Leroy, Romain Brégier +2

CVPR 2024poster

Human perception and understanding is a major domain of computer vision which like many other vision subdomains recently stands to gain from the use of large models pre-trained on large datasets. We hypothesize that the most common pre-training strategy of relying on general purpose object-centric i…

Cited by 5 Source ↗PDF ↗Scholar ↗

2024

Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot

Fabien Baradel*, Thomas LUCAS, Matthieu Armando, Salma Galaaoui, Romain Brégier, Philippe Weinzaepfel +1

ECCV 2024poster

"We present , a strong model for multi-person 3D human mesh recovery from a single RGB image. Predictions encompass the whole body, , including hands and facial expressions, using the SMPL-X parametric model and 3D location in the camera coordinate system. Our model detects people by predicting coar…

Cited by 27 Source ↗PDF ↗code ↗Scholar ↗

2024

UNIC: Universal Classification Models via Multi-teacher Distillation

Yannis Kalantidis, Diane Larlus, Mert Bulent Sariyildiz*, Philippe Weinzaepfel, Thomas LUCAS

ECCV 2024poster

"Pretrained models have become a commodity and offer strong results on a broad range of tasks. In this work, we focus on classification and seek to learn a unique encoder able to take from several complementary pretrained models. We aim at even stronger generalization across a variety of classificat…

Cited by 6 Source ↗PDF ↗Scholar ↗

2024

Win-Win: Training High-Resolution Vision Transformers from Two Windows

Vincent Leroy, Jerome Revaud, Thomas Lucas, Philippe Weinzaepfel

ICLR 2024poster

Transformers have become the standard in state-of-the-art vision architectures, achieving impressive performance on both image-level and dense pixelwise tasks. However, training vision transformers for high-resolution pixelwise tasks has a prohibitive cost. Typical solutions boil down to hierarchica…

Cited by 4 Source ↗PDF ↗Scholar ↗

2023

CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow

Philippe Weinzaepfel, Thomas Lucas, Vincent Leroy, Yohann Cabon, Vaibhav Arora, Romain Brégier +4

ICCV 2023poster

Despite impressive performance for high-level downstream tasks, self-supervised pre-training methods have not yet fully delivered on dense geometric vision tasks such as stereo matching or optical flow. The application of self-supervised concepts, such as instance discrimination or masked image mode…

Cited by 100 PDF ↗code ↗Scholar ↗

2022

Barely-Supervised Learning: Semi-supervised Learning with Very Few Labeled Images

Thomas Lucas, Philippe Weinzaepfel, Gregory Rogez

AAAI 2022technical

This paper tackles the problem of semi-supervised learning when the set of labeled samples is limited to a small number of images per class, typically less than 10, problem that we refer to as barely-supervised learning. We analyze in depth the behavior of a state-of-the-art semi-supervised method,…

Cited by 32 Source ↗PDF ↗Scholar ↗

2022

CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion

Philippe Weinzaepfel, Vincent Leroy, Thomas Lucas, Romain Brégier, Yohann Cabon, Vaibhav ARORA +4

NeurIPS 2022accept

Masked Image Modeling (MIM) has recently been established as a potent pre-training paradigm. A pretext task is constructed by masking patches in an input image, and this masked content is then predicted by a neural network using visible patches as sole input. This pre-training leads to state-of-the-…

Cited by 77 Source ↗PDF ↗code ↗Scholar ↗

2022

Learning Super-Features for Image Retrieval

Philippe Weinzaepfel, Thomas Lucas, Diane Larlus, Yannis Kalantidis

ICLR 2022poster

Methods that combine local and global features have recently shown excellent performance on multiple challenging deep image retrieval benchmarks, but their use of local features raises at least two issues. First, these local features simply boil down to the localized map activations of a neural netw…

Cited by 59 Source ↗PDF ↗code ↗Scholar ↗

2022

PoseGPT: Quantization-Based 3D Human Motion Generation and Forecasting

Thomas Lucas, Fabien Baradel, Philippe Weinzaepfel, Grégory Rogez

ECCV 2022poster

"We address the problem of action-conditioned generation of human motion sequences. Existing work falls into two categories: forecast models conditioned on observed past motions, or generative models conditioned action labels and duration only. In contrast, we generate motion conditioned on observat…

Cited by 88 Source ↗PDF ↗code ↗Scholar ↗

2022

PoseScript: 3D Human Poses from Natural Language

Ginger Delmas, Philippe Weinzaepfel, Thomas Lucas, Francesc Moreno-Noguer, Grégory Rogez

ECCV 2022poster

"Natural language is leveraged in many computer vision tasks such as image captioning, cross-modal retrieval or visual question answering, to provide fine-grained semantic information. While human pose is key to human understanding, current 3D human pose datasets lack detailed language descriptions.…

Cited by 66 Source ↗PDF ↗Scholar ↗

2019

Adaptive Density Estimation for Generative Models

Thomas Lucas, Konstantin Shmelkov, Karteek Alahari, Cordelia Schmid, Jakob Verbeek

NeurIPS 2019spotlight

Unsupervised learning of generative models has seen tremendous progress over recent years, in particular due to generative adversarial networks (GANs), variational autoencoders, and flow-based models. GANs have dramatically improved sample quality, but suffer from two drawbacks: (i) they mode-drop,…

Cited by 30 Source ↗PDF ↗Scholar ↗

2018

Mixed batches and symmetric discriminators for GAN training

Thomas LUCAS, Corentin Tallec, Yann Ollivier, Jakob Verbeek

ICML 2018oral

Generative adversarial networks (GANs) are pow- erful generative models based on providing feed- back to a generative network via a discriminator network. However, the discriminator usually as- sesses individual samples. This prevents the dis- criminator from accessing global distributional statisti…

Cited by 43 Source ↗PDF ↗Scholar ↗

2017

Areas of Attention for Image Captioning

Marco Pedersoli, Thomas Lucas, Cordelia Schmid, Jakob Verbeek

ICCV 2017poster

We propose "Areas of Attention", a novel attention-based model for automatic image captioning. Our approach models the dependencies between image regions, caption words, and the state of an RNN language model, using three pairwise interactions. In contrast to previous attention-based approaches that…

Cited by 267 PDF ↗Scholar ↗