Publications by Mathieu Salzmann

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Many classical Computer Vision problems, such as essential matrix computation and pose estimation from 3D to 2D correspondences, can be tackled by solving a linear least-square problem, which can be done by finding the eigenvector corresponding to the smal ...

We present GigaPose, a fast, robust, and accurate method for CAD-based novel object pose estimation in RGB images. GigaPose first leverages discriminative "templates", rendered images of the CAD models, to recover the out-of-plane rotation and then uses pa ...

Digitization and preservation of large heritage induce high maintenance costs to keep up with the technical standards and ensure sustainable access. Creating impactful usage is instrumental to justify the resources for long-term preservation. The Museum fü ...

Estimating the 6-degrees-of-freedom (6DoF) pose of a spacecraft from a single image is critical for autonomous operations like in-orbit servicing and space debris removal. Existing state-of-the-art methods often rely on iterative Perspective-n-Point (PnP)-based algorithms, which are computationally intensive and ill-suited for real-time deployment on resource-constrained edge devices. To overcome these limitations, we propose FastPose-ViT, a Vision Transformer (ViT)-based architecture that directly regresse

This paper explores Machine Learning (ML) parameterizations for radiative transfer in the ICOsahedral Nonhydrostatic weather and climate model (ICON) and investigates the achieved ML model speed‐up with ICON running on graphics processing units (GPUs). Five ML models, with varying complexity and size, are coupled to ICON; more specifically, a multilayer perceptron (MLP), a Unet model, a bidirectional recurrent neural network with long short‐term memory (BiLSTM), a vision transformer (ViT), and a random fore

While domain adaptation has been used to improve the performance of object detectors when the training and test data follow different distributions, previous work has mostly focused on two-stage detectors. This is because their use of region proposals make ...

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 ...

We introduce the task of action-driven stochastic human motion prediction, which aims to predict multiple plausible future motions given a sequence of action labels and a short motion history. This differs from existing works, which predict motions that ei ...

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 ...

We present a novel pipeline that uses a convolutional neural network (CNN) to improve the detection capability of near-Earth asteroids (NEAs) in the context of planetary defense. Our work aims to minimize the dependency on human intervention of the current ...

When enough annotated training data is available, supervised deep-learning. algorithms excel at estimating human body pose and shape using a single camera. The effects of too little such data being available can be mitigated by using other information sour ...

With increased availability of high quality diverse weather data, including reanalysis, satellite, surface stations, climate model data, the amount of data-driven foundation models (FM) in the environmental field has increased significantly over the past years with forecasting performances matching and sometimes exceeding physics-based numerical model predictions. However, most FMs are trained with one dataset or a few datasets with similar sampling and/or resolution properties. While the proposed models ac

Multi-label submodular Markov Random Fields (MRFs) have been shown to be solvable using max-flow based on an encoding of the labels proposed by Ishikawa, in which each variable X-i is represented by l nodes (where l is the number of labels) arranged in a c ...

The current leading 6D object pose estimation methods rely heavily on annotated real data, which is highly costly to acquire. To overcome this, many works have proposed to introduce computer-generated synthetic data. However, bridging the gap between the s ...

One of the limitations of applying machine learning methods in real-world scenarios is the existence of a domain shift between the source (i.e., training) and target (i.e., test) datasets, which typically entails a significant performance drop. This is further complicated by the lack of annotated data in the target domain, making it impossible to quantitatively assess the model performance. As such, there is a pressing need for methods able to estimate a model’s performance on unlabeled target data. Most of

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 ...

We propose a method for unsupervised reconstruction of a temporally-consistent sequence of surfaces from a sequence of time-evolving point clouds. It yields dense and semantically meaningful correspondences between frames. We represent the reconstructed su ...

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 ...

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 ...

Human motion prediction, i.e., forecasting future body poses given observed pose sequence, has typically been tackled with recurrent neural networks (RNNs). However, as evidenced by prior work, the resulted RNN models suffer from prediction errors accumula ...

Mathieu Salzmann

Chat with Graph Search

Eigendecomposition-Free Training of Deep Networks for Linear Least-Square Problems

GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

Automatic Content Curation of Visual Heritage

FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation

Revisiting Machine Learning Approaches for Short‐ and Longwave Radiation Inference in Weather and Climate Models

Attention-based domain adaptation for single-stage detectors

Counting People by Estimating People Flows

Weakly-supervised Action Transition Learning for Stochastic Human Motion Prediction

Perspective Aware Road Obstacle Detection

Deep Learning to Improve the Discovery of Near-earth Asteroids in the Zwicky Transient Facility

Using Motion Cues to Supervise Single-Frame Body Pose and Shape Estimation in Low Data Regimes

ESFM - A foundation model framework for heterogeneous data integration

Memory Efficient Max Flow for Multi-Label Submodular MRFs

SD-Pose: Semantic Decomposition for Cross-Domain 6D Object Pose Estimation

Leveraging Gradient Information for Out-of-Domain Performance Estimations

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

Temporally-Consistent Surface Reconstruction Using Metrically-Consistent Atlases

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

Dense Multitask Learning to Reconfigure Comics

Learning Trajectory Dependencies for Human Motion Prediction