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.

In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety and generalize to new domains. However, existing methods often struggle to distinguish between domainlevel and semantic-level distribution shifts, leading to poor out-of-distribution (OOD) detection or domain generalization performance. In this work, we aim to equip the model to generalize effectively to covariate-shift regions while precisely identifying semantic-shi

Recent years have seen the development of mature solutions for reconstructing deformable surfaces from a single image, provided that they are relatively well-textured. By contrast, recovering the 3D shape of texture-less surfaces remains an open problem, a ...

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 ...

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 ...

Determining the relative pose of an object between two images is pivotal to the success of generalizable object pose estimation. Existing approaches typically approximate the continuous pose representation with a large number of discrete pose hypotheses, w ...

We introduce an approach to training a given compact network. To this end, we leverage over-parameterization, which typically improves both neural network optimization and generalization. Specifically, we propose to expand each linear layer of the compact ...

State-of-the-art methods for counting people in crowded scenes rely on deep networks to estimate crowd density in the image plane. While useful for this purpose, this image- plane density has no immediate physical meaning because it is subject to perspecti ...

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 ...

We propose a method for the unsupervised reconstruction of a temporally-coherent sequence of surfaces from a sequence of time-evolving point clouds, yielding dense, semantically meaningful correspondences between all keyframes. We represent the reconstruct ...

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 ...

Correspondence pruning aims to correctly remove false matches (outliers) from an initial set of putative correspondences. The pruning process is challenging since putative matches are typically extremely unbalanced, largely dominated by outliers, and the r ...

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 ...

Here we provide the data of our article "HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields". It contains the rendered images and the segmentation masks that we use to train our model on HO3Dv2 dataset. The overall str ...

In the realm of point cloud scene understanding, particularly in indoor scenes, objects are arranged following human habits, resulting in objects of certain semantics being closely positioned and displaying notable inter-object correlations. This can creat ...

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 ...

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 ...

Two main classes of approaches have been studied to perform monocular nonrigid 3D reconstruction: Template-based methods and Non-rigid Structure from Motion techniques. While the first ones have been applied to reconstruct poorly-textured surfaces, they as ...

The high temporal variation of the point clouds is the key challenge of 3D single-object tracking (3D SOT). Existing approaches rely on the assumption that the shape variation of the point clouds and the motion of the objects across neighboring frames are ...

Self-supervised detection and segmentation of foreground objects aims for accuracy without annotated training data. However, existing approaches predominantly rely on restrictive assumptions on appearance and motion. For scenes with dynamic activities and ...

Adversarial attacks have been widely studied for general classification tasks, but remain unexplored in the context of fine-grained recognition, where the inter-class similarities facilitate the attacker's task. In this paper, we identify the proximity of ...

Mathieu Salzmann

Chat with Graph Search

Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts

Learning to Reconstruct Texture-less Deformable Surfaces from a Single View

Modeling Object Dissimilarity for Deep Saliency Prediction

3D Pose Based Feedback For Physical Exercises

Dvmnet: Computing Relative Pose for Unseen Objects Beyond Hypotheses

ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks

Geometric and Physical Constraints for Drone-Based Head Plane Crowd Density Estimation

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

Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases

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

Progressive Correspondence Pruning by Consensus Learning

Poster World. Bespoke AI Meets Curator Expertise for Public Engagement

Synthetic data (Part 2) for "HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields"

Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange

Learning Transformations To Reduce the Geometric Shift in Object Detection

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

Template-free 3D Reconstruction of Poorly-textured Nonrigid Surfaces

3D Single-Object Tracking in Point Clouds with High Temporal Variation

Human Detection and Segmentation via Multi-view Consensus

Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features