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.

The difficulty of obtaining annotations to build training databases still slows down the adoption of recent deep learning approaches for biomedical image analysis. In this paper, we show that we can train a Deep Net to perform 3D volumetric delineation giv ...

Weather foundation models are increasingly expected to operate under heterogeneous and imperfect observation settings while remaining computationally scalable. Building on the Earth System Foundation Model (ESFM) setting for heterogeneous data integration, we explore how Mixture-of-Experts (MoE) can support robust and efficient learning in multi-modal weather foundation models.We introduce ESFM-MoE, an exploratory direction that combines conditional computation with climate-semantic routing, a routing princ

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 ...

Latent variable models provide valuable compact representations for learning and inference in many computer vision tasks. However, most existing models cannot directly encode prior knowledge about the specific problem at hand. In this paper, we introduce a constrained latent variable model whose generated output inherently accounts for such knowledge. To this end, we propose an approach that explicitly imposes equality and inequality constraints on the model's output during learning, thus avoiding the compu

Most recent 6D pose estimation frameworks first rely on a deep network to establish correspondences between 3D object keypoints and 2D image locations and then use a variant of a RANSAC-based Perspective-n-Point (PnP) algorithm. This two-stage process, how ...

We propose the Subtractive Modulative Network (SMN), a novel, parameter-efficient Implicit Neural Representation (INR) architecture inspired by classical subtractive synthesis. The SMN is designed as a principled signal processing pipeline, featuring a learnable periodic activation layer (Oscillator) that generates a multi-frequency basis, and a series of modulative mask modules (Filters) that actively generate high-order harmonics. We provide both theoretical analysis and empirical validation for our desig

While Physics-Based Simulation (PBS) can accurately drape a 3D garment on a 3D body, it remains too costly for real-time applications, such as virtual try-on. By contrast, inference in a deep network, requiring a single forward pass, is much faster. Taking ...

Catastrophic mass movements, such as rock avalanches, glacier collapses, and destructive debris flows, are typically rare events. Their detection is consequently challenging as annotated and verified events used as training data for instrumentation and algorithm tuning are absent or limited. In this work, we explore seismic mass-movement data through the lens of anomaly detection. The idea is to screen out segments of the data that are unlikely to contain mass movements by focusing only on anomalous signals

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 ...

Eigendecomposition (ED) is widely used in deep networks. However, the backpropagation of its results tends to be numerically unstable, whether using ED directly or approximating it with the Power Iteration method, particularly when dealing with large matri ...

We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performance of previously-trained models degrades as one optimizes a subsequent one, ...

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 ...

Modern object detection methods typically rely on bounding box proposals as input. While initially popularized in the 2D case, this idea has received increasing attention for 3D bounding boxes. Nevertheless, existing 3D box proposal techniques all assume h ...

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 ...

Learning general image representations has proven key to the success of many computer vision tasks. For example, many approaches to image understanding problems rely on deep networks that were initially trained on ImageNet, mostly because the learned featu ...

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 edge detection. Based on the Swin transformer model, our framework encodes the input image into a shared representation and makes predictions for each vision task using task-specific transformer-based decoder heads. At the heart of our approach is a shared at

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 ...

Analyzing and training 3D body posture models depend heavily on the availability of joint labels that are commonly acquired through laborious manual annotation of body joints or via marker-based joint localization using carefully curated markers and capturing systems. However, such annotations are not always available, especially for people performing unusual activities. In this paper, we propose an algorithm that learns to discover 3D keypoints on human bodies from multiple-view images without any supervis

Mathieu Salzmann

Chat with Graph Search

Tracing in 2D to reduce the annotation effort for 3D deep delineation of linear structures

ESFM-MoE: Climate-semantic routing for Earth System Foundation Model (ESFM)

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

A Constrained Latent Variable Model

Single-Stage 6D Object Pose Estimation

Subtractive Modulative Network with Learnable Periodic Activations

GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping

Exploring seismic mass-movement data with anomaly detection and dynamic time warping

Exploring seismic mass-movement data with anomaly detection and dynamic time warping

MulT: An End-to-End Multitask Learning Transformer

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

Backpropagation-Friendly Eigendecomposition

Overcoming Multi-model Forgetting

Rigidity-Aware Detection for 6D Object Pose Estimation

3D Box Proposals from a Single Monocular Image of an Indoor Scene

TempSAL - Uncovering Temporal Information for Deep Saliency Prediction

Neural Scene Decomposition for Multi-Person Motion Capture

MulT: An End-to-End Multitask Learning Transformer

Robust Outlier Rejection for 3D Registration with Variational Bayes

Unsupervised 3D Keypoint Discovery with Multi-View Geometry