322 citations · 1.5k across the 74 of their papers we have counts for
84 papers
LightDepth: Single-View Depth Self-Supervision from Illumination Decline
Javier Rodríguez-Puigvert, Víctor M. Batlle, J. M. M. Montiel +4
Single-view depth estimation can be remarkably effective if there is enough ground-truth depth data for supervised training. However, there are scenarios, especially in medicine in…
LightNeuS: Neural Surface Reconstruction in Endoscopy using Illumination Decline
Víctor M. Batlle, José M. M. Montiel, Pascal Fua +1
We propose a new approach to 3D reconstruction from sequences of images acquired by monocular endoscopes. It is based on two key insights. First, endoluminal cavities are watertigh…
Pairwise-Constrained Implicit Functions for 3D Human Heart Modelling
Hieu Le, Jingyi Xu, Nicolas Talabot +2
Accurate 3D models of the human heart require not only correct outer surfaces but also realistic inner structures, such as the ventricles, atria, and myocardial layers. Approaches…
Automatic Parameterization for Aerodynamic Shape Optimization via Deep Geometric Learning
Zhen Wei, Pascal Fua, Michaël Bauerheim
We propose two deep learning models that fully automate shape parameterization for aerodynamic shape optimization. Both models are optimized to parameterize via deep geometric lear…
ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns
Ren Li, Benoît Guillard, Pascal Fua
Many approaches to draping individual garments on human body models are realistic, fast, and yield outputs that are differentiable with respect to the body shape on which they are…
GECCO: Geometrically-Conditioned Point Diffusion Models
Michał J. Tyszkiewicz, Pascal Fua, Eduard Trulls
Diffusion models generating images conditionally on text, such as Dall-E 2 and Stable Diffusion, have recently made a splash far beyond the computer vision community. Here, we tack…
PartAL: Efficient Partial Active Learning in Multi-Task Visual Settings
Nikita Durasov, Nik Dorndorf, Pascal Fua
Multi-task learning is central to many real-world applications. Unfortunately, obtaining labelled data for all tasks is time-consuming, challenging, and expensive. Active Learning…
Unsupervised 3D Keypoint Discovery with Multi-View Geometry
Sina Honari, Chen Zhao, Mathieu Salzmann +1
Analyzing and training 3D body posture models depend heavily on the availability of joint labels that are commonly acquired through laborious manual annotation of body joints or vi…
ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference
Nikita Durasov, Nik Dorndorf, Hieu Le +1
Whereas the ability of deep networks to produce useful predictions has been amply demonstrated, estimating the reliability of these predictions remains challenging. Sampling approa…
DrapeNet: Garment Generation and Self-Supervised Draping
Luca De Luigi, Ren Li, Benoît Guillard +2
Recent approaches to drape garments quickly over arbitrary human bodies leverage self-supervision to eliminate the need for large training sets. However, they are designed to train…
Two-level Data Augmentation for Calibrated Multi-view Detection
Martin Engilberge, Haixin Shi, Zhiye Wang +1
Data augmentation has proven its usefulness to improve model generalization and performance. While it is commonly applied in computer vision application when it comes to multi-view…
State of the Art in Dense Monocular Non-Rigid 3D Reconstruction
Edith Tretschk, Navami Kairanda, Mallikarjun B R +7
3D reconstruction of deformable (or non-rigid) scenes from a set of monocular 2D image observations is a long-standing and actively researched area of computer vision and graphics.…
Perspective Aware Road Obstacle Detection
Krzysztof Lis, Sina Honari, Pascal Fua +1
While road obstacle detection techniques have become increasingly effective, they typically ignore the fact that, in practice, the apparent size of the obstacles decreases as their…
DIG: Draping Implicit Garment over the Human Body
Ren Li, Benoît Guillard, Edoardo Remelli +1
Existing data-driven methods for draping garments over human bodies, despite being effective, cannot handle garments of arbitrary topology and are typically not end-to-end differen…
Learning to Simulate Realistic LiDARs
Benoit Guillard, Sai Vemprala, Jayesh K. Gupta +4
Simulating realistic sensors is a challenging part in data generation for autonomous systems, often involving carefully handcrafted sensor design, scene properties, and physics mod…
3D Pose Based Feedback for Physical Exercises
Ziyi Zhao, Sena Kiciroglu, Hugues Vinzant +4
Unsupervised self-rehabilitation exercises and physical training can cause serious injuries if performed incorrectly. We introduce a learning-based framework that identifies the mi…
Neural Annotation Refinement: Development of a New 3D Dataset for Adrenal Gland Analysis
Jiancheng Yang, Rui Shi, Udaranga Wickramasinghe +3
The human annotations are imperfect, especially when produced by junior practitioners. Multi-expert consensus is usually regarded as golden standard, while this annotation protocol…
Enforcing connectivity of 3D linear structures using their 2D projections
Doruk Oner, Hussein Osman, Mateusz Kozinski +1
Many biological and medical tasks require the delineation of 3D curvilinear structures such as blood vessels and neurites from image volumes. This is typically done using neural ne…
Deep Active Latent Surfaces for Medical Geometries
Patrick M. Jensen, Udaranga Wickramasinghe, Anders B. Dahl +2
Shape priors have long been known to be effective when reconstructing 3D shapes from noisy or incomplete data. When using a deep-learning based shape representation, this often inv…
On Triangulation as a Form of Self-Supervision for 3D Human Pose Estimation
Soumava Kumar Roy, Leonardo Citraro, Sina Honari +1
Supervised approaches to 3D pose estimation from single images are remarkably effective when labeled data is abundant. However, as the acquisition of ground-truth 3D labels is labo…
Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation
Yinlin Hu, Pascal Fua, Mathieu Salzmann
Most recent 6D object pose estimation methods, including unsupervised ones, require many real training images. Unfortunately, for some applications, such as those in space or deep…
Overcoming the Domain Gap in Neural Action Representations
Semih Günel, Florian Aymanns, Sina Honari +2
Relating animal behaviors to brain activity is a fundamental goal in neuroscience, with practical applications in building robust brain-machine interfaces. However, the domain gap…
Dyadic Human Motion Prediction
Isinsu Katircioglu, Costa Georgantas, Mathieu Salzmann +1
Prior work on human motion forecasting has mostly focused on predicting the future motion of single subjects in isolation from their past pose sequence. In the presence of closely…
Adversarial Parametric Pose Prior
Andrey Davydov, Anastasia Remizova, Victor Constantin +3
The Skinned Multi-Person Linear (SMPL) model can represent a human body by mapping pose and shape parameters to body meshes. This has been shown to facilitate inferring 3D human po…