356 citations · 1.3k across the 40 of their papers we have counts for
49 papers
BLASt3R: Bundle Adjustment of Any Image Set with Multi-View Matching and Monocular Priors
Vincent Leroy, Philippe Weinzaepfel, Lojze Zust +2
Recent hybrid Structure-from-Motion (SfM) systems combine the robustness of feed-forward 3D reconstruction with the accuracy of traditional bundle adjustment (BA) with pixel matchi…
Sparse auto-regressive modeling for scene generation from multi-view images
Thomas Lucas, Maxime Pietrantoni, Philippe Weinzaepfel +4
Generating complete 3D scenes from sparse, unconstrained views is a fundamental challenge in 3D vision which requires reasoning beyond observed content while remaining computationa…
Compressing History into Memory: Distilling Transformers into Recurrent Transformers
Philippe Weinzaepfel, Christian Wolf, Bülent Mert Sariyildiz +3
Transformers are AI's workhorse but their computational cost becomes prohibitive when processing long sequences. We target long-horizon streaming vision and robotics applications,…
Multi-HMR 2: Multi-Person Camera-Centric Human Detection, Mesh Recovery and Tracking
Guénolé Fiche, Philippe Weinzaepfel, Romain Brégier +1
Most advances in human mesh recovery (HMR) have focused on pelvis-centered recovery, overlooking metric 3D localization and detection accuracy in the camera coordinate system - two…
Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks
Pau de Jorge, César Roberto de Souza, Björn Michele +5
Efficiently merging several models fine-tuned for different tasks, but stemming from the same pretrained base model, is of great practical interest. Despite extensive prior work, m…
Human Mesh Modeling for Anny Body
Romain Brégier, Guénolé Fiche, Laura Bravo-Sánchez +5
Parametric body models provide the structural basis for many human-centric tasks, yet existing models often rely on costly 3D scans and learned shape spaces that are proprietary an…
Kinaema: a recurrent sequence model for memory and pose in motion
Mert Bulent Sariyildiz, Philippe Weinzaepfel, Guillaume Bono +2
One key aspect of spatially aware robots is the ability to "find their bearings", ie. to correctly situate themselves in previously seen spaces. In this work, we focus on this part…
HOSt3R: Keypoint-free Hand-Object 3D Reconstruction from RGB images
Anilkumar Swamy, Vincent Leroy, Philippe Weinzaepfel +2
Hand-object 3D reconstruction has become increasingly important for applications in human-robot interaction and immersive AR/VR experiences. A common approach for object-agnostic h…
HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction
Sara Rojas, Matthieu Armando, Bernard Ghamen +3
Recovering the 3D geometry of a scene from a sparse set of uncalibrated images is a long-standing problem in computer vision. While recent learning-based approaches such as DUSt3R…
What does really matter in image goal navigation?
Gianluca Monaci, Philippe Weinzaepfel, Christian Wolf
Image goal navigation requires two different skills: firstly, core navigation skills, including the detection of free space and obstacles, and taking decisions based on an internal…
DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers
Mert Bulent Sariyildiz, Philippe Weinzaepfel, Thomas Lucas +3
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…
Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors
Wonbong Jang, Philippe Weinzaepfel, Vincent Leroy +2
We present Pow3r, a novel large 3D vision regression model that is highly versatile in the input modalities it accepts. Unlike previous feed-forward models that lack any mechanism…
CondiMen: Conditional Multi-Person Mesh Recovery
Brégier Romain, Baradel Fabien, Lucas Thomas +4
Multi-person human mesh recovery (HMR) consists in detecting all individuals in a given input image, and predicting the body shape, pose, and 3D location for each detected person.…
MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion
Bardienus Duisterhof, Lojze Zust, Philippe Weinzaepfel +3
Structure-from-Motion (SfM), a task aiming at jointly recovering camera poses and 3D geometry of a scene given a set of images, remains a hard problem with still many open challeng…
PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation
Ginger Delmas, Philippe Weinzaepfel, Francesc Moreno-Noguer +1
Aligning multiple modalities in a latent space, such as images and texts, has shown to produce powerful semantic visual representations, fueling tasks like image captioning, text-t…
UNIC: Universal Classification Models via Multi-teacher Distillation
Mert Bulent Sariyildiz, Philippe Weinzaepfel, Thomas Lucas +2
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 ta…
Purposer: Putting Human Motion Generation in Context
Nicolas Ugrinovic, Thomas Lucas, Fabien Baradel +3
We present a novel method to generate human motion to populate 3D indoor scenes. It can be controlled with various combinations of conditioning signals such as a path in a scene, t…
Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
Yannis Kalantidis, Mert Bülent Sarıyıldız, Rafael S. Rezende +3
State-of-the-art visual localization approaches generally rely on a first image retrieval step whose role is crucial. Yet, retrieval often struggles when facing varying conditions,…
Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot
Fabien Baradel, Matthieu Armando, Salma Galaaoui +4
We present Multi-HMR, a strong sigle-shot model for multi-person 3D human mesh recovery from a single RGB image. Predictions encompass the whole body, i.e., including hands and fac…
Cross-view and Cross-pose Completion for 3D Human Understanding
Matthieu Armando, Salma Galaaoui, Fabien Baradel +5
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 o…
Win-Win: Training High-Resolution Vision Transformers from Two Windows
Vincent Leroy, Jerome Revaud, Thomas Lucas +1
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 vi…
End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon
Guillaume Bono, Leonid Antsfeld, Boris Chidlovskii +2
Most recent work in goal oriented visual navigation resorts to large-scale machine learning in simulated environments. The main challenge lies in learning compact representations g…
SHOWMe: Benchmarking Object-agnostic Hand-Object 3D Reconstruction
Anilkumar Swamy, Vincent Leroy, Philippe Weinzaepfel +6
Recent hand-object interaction datasets show limited real object variability and rely on fitting the MANO parametric model to obtain groundtruth hand shapes. To go beyond these lim…
PoseFix: Correcting 3D Human Poses with Natural Language
Ginger Delmas, Philippe Weinzaepfel, Francesc Moreno-Noguer +1
Automatically producing instructions to modify one's posture could open the door to endless applications, such as personalized coaching and in-home physical therapy. Tackling the r…