Home

Person

Mathieu Salzmann

About
Privacy
Disclaimer

Graph Chatbot

Related publications (169)

Center-aware Adversarial Augmentation for Single Domain Generalization

Domain generalization (DG) aims to learn a model from multiple training (i.e., source) domains that can generalize well to the unseen test (i.e., target) data coming from a different distribution. Single domain generalization (SingleDG) has recently emerge ...

IEEE COMPUTER SOC2023

Center-Based Decoupled Point Cloud Registration for 6D Object Pose Estimation

Mathieu Salzmann, Zheng Dang, Jiancheng Yang, Haobo Jiang

In this paper, we propose a novel center-based decoupled point cloud registration framework for robust 6D object pose estimation in real-world scenarios. Our method decouples the translation from the entire transformation by predicting the object center an ...

Ieee Computer Soc2023

Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation

Mathieu Salzmann, Yinlin Hu, Fulin Liu

Most modern image-based 6D object pose estimation methods learn to predict 2D-3D correspondences, from which the pose can be obtained using a PnP solver. Because of the non-differentiable nature of common PnP solvers, these methods are supervised via the i ...

Ieee Computer Soc2023

Rigidity-Aware Detection for 6D Object Pose Estimation

Mathieu Salzmann, Yinlin Hu, Rui Song, Jingyu Li

Most recent 6D object pose estimation methods first use object detection to obtain 2D bounding boxes before actually regressing the pose. However, the general object detection methods they use are ill-suited to handle cluttered scenes, thus producing poor ...

Ieee Computer Soc2023

MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency

Mathieu Salzmann, Kun Sun, Yunhua Zhang, Jiancheng Yang

3D single object tracking (SOT) is an indispensable part of automated driving. Existing approaches rely heavily on large, densely labeled datasets. However, annotating point clouds is both costly and time-consuming. Inspired by the great success of cycle t ...

Ieee Computer Soc2023

Adversarial Parametric Pose Prior

Pascal Fua, Mathieu Salzmann, Victor Constantin, Andrey Davydov, Sina Honari, Anastasia Remizova

The Skinned Multi-Person Linear (SMPL) model represents human bodies by mapping pose and shape parameters to body meshes. However, not all pose and shape parameter values yield physically-plausible or even realistic body meshes. In other words, SMPL is und ...

IEEE2022

Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions

Mathieu Salzmann, Vincent Lepetit, Yinlin Hu, Van Nguyen Nguyen, Yang Xiao

We present a method that can recognize new objects and estimate their 3D pose in RGB images even under partial occlusions. Our method requires neither a training phase on these objects nor real images depicting them, only their CAD models. It relies on a s ...

IEEE COMPUTER SOC2022

Temporal Representation Learning on Monocular Videos for 3D Human Pose Estimation

Pascal Fua, Mathieu Salzmann, Victor Constantin, Helge Jochen Rhodin, Sina Honari

In this paper we propose an unsupervised feature extraction method to capture temporal information on monocular videos, where we detect and encode subject of interest in each frame and leverage contrastive self-supervised (CSS) learning to extract rich lat ...

2022

Poster World. Bespoke AI Meets Curator Expertise for Public Engagement

Mathieu Salzmann, Nicolas Henchoz, Delphine Ribes Lemay, Emily Clare Groves, Andrea Regula Schneider

Though museums are digitising their archives, online consultations remain low. New forms of engagement bring these digital memories to life and can support museums in maintaining and developing digital resources. Artificial Intelligence presents opportunit ...

2022

Counting People by Estimating People Flows

Pascal Fua, Mathieu Salzmann, Weizhe Liu

Modern methods for counting people in crowded scenes rely on deep networks to estimate people densities in individual images. As such, only very few take advantage of temporal consistency in video sequences, and those that do only impose weak smoothness co ...

2022

Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy

Mathieu Salzmann, Sabine Süsstrunk, Tong Zhang

Self-supervised learning (SSL) methods aim to learn view-invariant representations by maximizing the similarity between the features extracted from different crops of the same image regardless of cropping size and content. In essence, this strategy ignores ...

IEEE COMPUTER SOC2022

GarNet++: Improving Fast and Accurate Static 3D Cloth Draping by Curvature Loss

Pascal Fua, Mathieu Salzmann, Victor Constantin, Erhan Gündogdu, Shaifali Parashar

In this paper, we tackle the problem of static 3D cloth draping on virtual human bodies. We introduce a two-stream deep network model that produces a visually plausible draping of a template cloth on virtual 3D bodies by extracting features from both the b ...

2022

Modeling Object Dissimilarity for Deep Saliency Prediction

Mathieu Salzmann, Sabine Süsstrunk, Bahar Aydemir, Deblina Bhattacharjee, Seungryong Kim, Tong Zhang

Saliency prediction has made great strides over the past two decades, with current techniques modeling low-level information, such as color, intensity and size contrasts, and high-level ones, such as attention and gaze direction for entire objects. Despite ...

2022

3D Pose Based Feedback For Physical Exercises

Pascal Fua, Mathieu Salzmann, Isinsu Katircioglu, Hugues François Rémi Vinzant, Sena Kiciroglu, Ziqi Zhao, Yuan Cheng, Ziyi Zhao

Unsupervised self-rehabilitation exercises and physical training can cause serious injuries if performed incorrectly. We introduce a learning-based framework that identifies the mistakes made by a user and proposes corrective measures for easier and safer ...

Springer2022

Fusing Local Similarities for Retrieval-based 3D Orientation Estimation of Unseen Objects

Mathieu Salzmann, Yinlin Hu, Chenxu Zhao

2022

Contrastive Class-aware Adaptation for Domain Generalization

Mathieu Salzmann

Domain generalization (DG) tackles the problem of learning a model that generalizes to data drawn from a target domain that was unseen during training. A major trend in this area consists of learning a domain-invariant representation by minimizing the disc ...

IEEE2022

MulT: An End-to-End Multitask Learning Transformer

Mathieu Salzmann, Sabine Süsstrunk, Deblina Bhattacharjee, Tong Zhang

We propose an end-to-end Multitask Learning Transformer framework, named MulT, to simultaneously learn multiple high-level vision tasks, including depth estimation, semantic segmentation, reshading, surface normal estimation, 2D keypoint detection, and edg ...

IEEE COMPUTER SOC2022

Long Term Motion Prediction Using Keyposes

Pascal Fua, Mathieu Salzmann, Sena Kiciroglu, Wei Wang

Long term human motion prediction is essential in safety-critical applications such as human-robot interaction and autonomous driving. In this paper we show that to achieve long term forecasting, predicting human pose at every time instant is unnecessary. ...

IEEE2022

Learning to Generate the Unknowns as a Remedy to the Open-Set Domain Shift

Mathieu Salzmann

In many situations, the data one has access to at test time follows a different distribution from the training data. Over the years, this problem has been tackled by closed-set domain adaptation techniques. Recently, open-set domain adaptation has emerged ...

IEEE COMPUTER SOC2022

Robust Binary Models by Pruning Randomly-initialized Networks

Mathieu Salzmann, Sabine Süsstrunk, Chen Liu, Ziqi Zhao

Robustness to adversarial attacks was shown to require a larger model capacity, and thus a larger memory footprint. In this paper, we introduce an approach to obtain robust yet compact models by pruning randomly-initialized binary networks. Unlike adversar ...

2022

Page 3 of 9