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.

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 ...

The most recent trend in estimating the 6D pose of rigid objects has been to train deep networks to either directly regress the pose from the image or to predict the 2D locations of 3D keypoints, from which the pose can be obtained using a PnP algorithm. I ...

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 ...

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. ...

Neural Architecture Search (NAS) aims to facilitate the design of deep networks fornew tasks. Existing techniques rely on two stages: searching over the architecture space and validating the best architecture. NAS algorithms are currently compared solely b ...

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 ...

We tackle unsupervised domain adaptation by accounting for the fact that different domains may need to be processed differently to arrive to a common feature representation effective for recognition. To this end, we introduce a deep learning framework wher ...

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as inliers or outlie ...

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 ...

Recently, parametric mappings have emerged as highly effective surface representations, yielding low reconstruction error. In particular, the latest works represent the target shape as an atlas of multiple mappings, which can closely encode object parts. A ...

3D Gaussian Splatting (3DGS) has demonstrated remarkable effectiveness in novel view synthesis (NVS). However, 3DGS tends to overfit when trained with sparse views, limiting its generalization to novel viewpoints. In this paper, we address this overfitting issue by introducing Self-Ensembling Gaussian Splatting (SE-GS). We achieve self-ensembling by incorporating an uncertainty-aware perturbation strategy during training. A Δ-model and a Σ-model are jointly trained on the available images. The Δ-model is dy

Image-to-image translation has made great strides in recent years, with current techniques being able to handle unpaired training images and to account for the multimodality of the translation problem. Despite this, most methods treat the image as a whole, ...

Here we provide the data of our article "HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields". It contains the preprocessed SDF samples. Meanwhile, we also include rendered data for HO3Dv2 here. The overall structure of ...

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 ...

Knowledge distillation constitutes a simple yet effective way to improve the performance of a compact student network by exploiting the knowledge of a more powerful teacher. Nevertheless, the knowledge distillation literature remains limited to the scenari ...

Mathieu Salzmann

Chat with Graph Search

Toward Automatic Typography Analysis: Serif Classification and Font Similarities

Segmentation-driven 6D Object Pose Estimation

Vision Transformer Adapters for Generalizable Multitask Learning

Long Term Motion Prediction Using Keyposes

Evaluating the search phase of neural architecture search

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

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

Domain-Adaptive Multibranch Networks

Learning to Find Good Correspondences

A Closed-Form Pairwise Solution to Local Non-Rigid Structure-from-Motion

Estimating People Flows to Better Count Them in Crowded Scenes

Better Patch Stitching for Parametric Surface Reconstruction

Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis

DUNIT: Detection-based Unsupervised Image-to-Image Translation

Imposing Hard Constraints on Deep Networks: Promises and Limitations

Synthetic data (Part 1) for "HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields"

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

Learning to Co-Generate Object Proposals with a Deep Structured Network

Distilling Image Classifiers in Object Detectors

Learning the Number of Neurons in Deep Networks