Home

Person

Mathieu Salzmann

About
Privacy
Disclaimer

Graph Chatbot

Related publications (169)

LiDAR-NeRF: Novel LiDAR View Synthesis via Neural Radiance Fields

We introduce a new task, novel view synthesis for LiDAR sensors. While traditional model-based LiDAR simulators with style-transfer neural networks can be applied to render novel views, they fall short of producing accurate and realistic LiDAR patterns bec ...

Association for Computing Machinery, Inc2024

Toward Automatic Typography Analysis: Serif Classification and Font Similarities

Mathieu Salzmann, Nicolas Henchoz, Delphine Ribes Lemay, Romain Simon Collaud, Syed Talal Wasim

Whether a document is of historical or contemporary significance, typography plays a crucial role in its composition. From the early days of modern printing, typographic techniques have evolved and transformed, resulting in changes to the features of typog ...

2024

TIC-TAC: A Framework for Improved Covariance Estimation in Deep Heteroscedastic Regression

Mathieu Salzmann, Alexandre Massoud Alahi, Megh Hiren Shukla

Deep heteroscedastic regression involves jointly optimizing the mean and covariance of the predicted distribution using the negative log-likelihood. However, recent works show that this may result in sub-optimal convergence due to the challenges associated ...

2024

Detecting Road Obstacles by Erasing Them

Pascal Fua, Mathieu Salzmann, Krzysztof Maciej Lis, Sina Honari

Vehicles can encounter a myriad of obstacles on the road, and it is impossible to record them all beforehand to train a detector. Instead, we select image patches and inpaint them with the surrounding road texture, which tends to remove obstacles from thos ...

2024

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields: Processed data and trained models

Mathieu Salzmann, Alexander Mathis

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields, CVPR 2024 Haozhe Qi, Chen Zhao, Mathieu Salzmann, Alexander Mathis. Affiliation: EPFL Date: June, 2024 Link to the CVPR article: https://openaccess.thecvf.com/conte ...

Zenodo2024

HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields

Mathieu Salzmann, Alexander Mathis

Human hands are highly articulated and versatile at handling objects. Jointly estimating the 3D poses of a hand and the object it manipulates from a monocular camera is challenging due to frequent occlusions. Thus, existing methods often rely on intermedia ...

IEEE2024

DrapeNet: Garment Generation and Self-Supervised Draping

Pascal Fua, Mathieu Salzmann, Benoît Alain René Guillard, Ren Li, Luca De Luigi

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 one network per clothing item, which severely limits their generalization a ...

IEEE2023

Robust Outlier Rejection for 3D Registration with Variational Bayes

Mathieu Salzmann, Zheng Dang, Zhen Wei, Jiancheng Yang, Haobo Jiang

Learning-based outlier (mismatched correspondence) rejection for robust 3D registration generally formulates the outlier removal as an inlier/outlier classification problem. The core for this to be successful is to learn the discriminative inlier/outlier f ...

Ieee Computer Soc2023

Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions

Mathieu Salzmann, Shuxuan Guo, Yinlin Hu

Knowledge distillation facilitates the training of a compact student network by using a deep teacher one. While this has achieved great success in many tasks, it remains completely unstudied for image-based 6D object pose estimation. In this work, we intro ...

Ieee Computer Soc2023

Vision Transformer Adapters for Generalizable Multitask Learning

Mathieu Salzmann, Sabine Süsstrunk, Deblina Bhattacharjee

We introduce the first multitasking vision transformer adapters that learn generalizable task affinities which can be applied to novel tasks and domains. Integrated into an off-the-shelf vision transformer backbone, our adapters can simultaneously solve mu ...

Ieee Computer Soc2023

TempSAL - Uncovering Temporal Information for Deep Saliency Prediction

Mathieu Salzmann, Sabine Süsstrunk, Bahar Aydemir, Tong Zhang

Deep saliency prediction algorithms complement the object recognition features, they typically rely on additional information such as scene context, semantic relationships, gaze direction, and object dissimilarity. However, none of these models consider th ...

Ieee Computer Soc2023

Learning Transformations To Reduce the Geometric Shift in Object Detection

Mathieu Salzmann, Martin Pierre Engilberge, Vidit Vidit

The performance of modern object detectors drops when the test distribution differs from the training one. Most of the methods that address this focus on object appearance changes caused by, e.g., different illumination conditions, or gaps between syntheti ...

Ieee Computer Soc2023

Dense Multitask Learning to Reconfigure Comics

Mathieu Salzmann, Sabine Süsstrunk, Deblina Bhattacharjee

In this paper, we develop a MultiTask Learning (MTL) model to achieve dense predictions for comic panels to, in turn, facilitate the transfer of comics from one publication channel to another by assisting authors in the task of reconfiguring their narrativ ...

IEEE2023

Spatiotemporal Self-supervised Learning for Point Clouds in the Wild

Mathieu Salzmann, Sabine Süsstrunk, Tong Zhang

Self-supervised learning (SSL) has the potential to ben- efit many applications, particularly those where manually annotating data is cumbersome. One such situation is the semantic segmentation of point clouds. In this context, ex- isting methods employ co ...

IEEE2023

Perspective Aware Road Obstacle Detection

Pascal Fua, Mathieu Salzmann, Krzysztof Maciej Lis, Sina Honari

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 distance to the vehicle increases. In this letter, we account for this by c ...

2023

AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration

Mathieu Salzmann, Zheng Dang

In the current deep learning paradigm, the amount and quality of training data are as critical as the network architecture and its training details. However, collecting, processing, and annotating real data at scale is difficult, expensive, and time-consum ...

Ieee Computer Soc2023

Fast Adversarial Training With Adaptive Step Size

Mathieu Salzmann, Sabine Süsstrunk, Jue Wang, Chen Liu, Yong Zhang, Zhuoyi Huang

While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet. The key idea of recent works to ...

Ieee-Inst Electrical Electronics Engineers Inc2023

Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks

Mathieu Salzmann, Sabine Süsstrunk, Chen Liu, Zhuoyi Huang, Yulun Jiang

We address the problem of stably and efficiently training a deep neural network robust to adversarial perturbations bounded by an

l_1

norm. We demonstrate that achieving robustness against

l_1

-bounded perturbations is more challenging than in the

l_2

...

2023

CLIP the Gap: A Single Domain Generalization Approach for Object Detection

Mathieu Salzmann, Martin Pierre Engilberge, Vidit Vidit

Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. While this has been well studied for image classification, the literature on SDG object detection remai ...

Ieee Computer Soc2023

Training Provably Robust Models by Polyhedral Envelope Regularization

Mathieu Salzmann, Sabine Süsstrunk, Chen Liu

Training certifiable neural networks enables us to obtain models with robustness guarantees against adversarial attacks. In this work, we introduce a framework to obtain a provable adversarial-free region in the neighborhood of the input data by a polyhedr ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2023

Page 2 of 9