Mathieu Salzmann

FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation WACV 2026 Free-Moving Object Reconstruction and Pose Estimation with Virtual Camera AAAI 2025 GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control CVPR 2025 Demystifying Singular Defects in Large Language Models ICML 2025 QT-DoG: Quantization-Aware Training for Domain Generalization ICML 2025 MotionMap: Representing Multimodality in Human Pose Forecasting CVPR 2025 Self-Ensembling Gaussian Splatting for Few-Shot Novel View Synthesis ICCV 2025 Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression ICLR 2025 Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds ICLR 2025 GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence CVPR 2024 On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Training JMLR 2024 TIC-TAC: A Framework For Improved Covariance Estimation In Deep Heteroscedastic Regression ICML 2024 Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts NIPS 2024 3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation ICLR 2024 Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised Learning ICLR 2024 Neural SDF Flow for 3D Reconstruction of Dynamic Scenes ICLR 2024 Source-Free Domain-Invariant Performance Prediction ECCV 2024 Data Augmentation via Latent Diffusion for Saliency Prediction ECCV 2024 3D Single-object Tracking in Point Clouds with High Temporal Variation ECCV 2024 SINDER: Repairing the Singular Defects of DINOv2 ECCV 2024 CLOAF: CoLlisiOn-Aware Human Flow CVPR 2024 DVMNet: Computing Relative Pose for Unseen Objects Beyond Hypotheses CVPR 2024 NOPE: Novel Object Pose Estimation from a Single Image CVPR 2024 Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange CVPR 2024 HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields CVPR 2024 Knowledge Distillation for 6D Pose Estimation by Aligning Distributions of Local Predictions CVPR 2023 Spatiotemporal Self-Supervised Learning for Point Clouds in the Wild CVPR 2023 TempSAL - Uncovering Temporal Information for Deep Saliency Prediction CVPR 2023 SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation NIPS 2023 Robust Outlier Rejection for 3D Registration With Variational Bayes CVPR 2023 Learning Transformations To Reduce the Geometric Shift in Object Detection CVPR 2023 Center-Aware Adversarial Augmentation for Single Domain Generalization WACV 2023 CLIP the Gap: A Single Domain Generalization Approach for Object Detection CVPR 2023 DrapeNet: Garment Generation and Self-Supervised Draping CVPR 2023 Towards Stable and Efficient Adversarial Training against $l_1$ Bounded Adversarial Attacks ICML 2023 Vision Transformer Adapters for Generalizable Multitask Learning ICCV 2023 Linear-Covariance Loss for End-to-End Learning of 6D Pose Estimation ICCV 2023 AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration ICCV 2023 Center-Based Decoupled Point-cloud Registration for 6D Object Pose Estimation ICCV 2023 MixCycle: Mixup Assisted Semi-Supervised 3D Single Object Tracking with Cycle Consistency ICCV 2023 Rigidity-Aware Detection for 6D Object Pose Estimation CVPR 2023 Fusing Local Similarities for Retrieval-Based 3D Orientation Estimation of Unseen Objects ECCV 2022 Robust Binary Models by Pruning Randomly-initialized Networks NIPS 2022 Contact-aware Human Motion Forecasting NIPS 2022 MulT: An End-to-End Multitask Learning Transformer CVPR 2022 Weakly-Supervised Action Transition Learning for Stochastic Human Motion Prediction CVPR 2022 Templates for 3D Object Pose Estimation Revisited: Generalization to New Objects and Robustness to Occlusions CVPR 2022 Adversarial Parametric Pose Prior CVPR 2022 Leverage Your Local and Global Representations: A New Self-Supervised Learning Strategy CVPR 2022 Learning-Based Point Cloud Registration for 6D Object Pose Estimation in the Real World ECCV 2022 Perspective Flow Aggregation for Data-Limited 6D Object Pose Estimation ECCV 2022 Estimating Image Depth in the Comics Domain WACV 2022 Learning To Generate the Unknowns as a Remedy to the Open-Set Domain Shift WACV 2022 Generating Smooth Pose Sequences for Diverse Human Motion Prediction ICCV 2021 Progressive Correspondence Pruning by Consensus Learning ICCV 2021 Contextually Plausible and Diverse 3D Human Motion Prediction ICCV 2021 Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases ICCV 2021 PCLs: Geometry-Aware Neural Reconstruction of 3D Pose With Perspective Crop Layers CVPR 2021 Landmark Regularization: Ranking Guided Super-Net Training in Neural Architecture Search CVPR 2021 Wide-Depth-Range 6D Object Pose Estimation in Space CVPR 2021 Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking CVPR 2021 Distilling Image Classifiers in Object Detectors NIPS 2021 Learning Transferable Adversarial Perturbations NIPS 2021 SD-Pose: Semantic Decomposition for Cross-Domain 6D Object Pose Estimation AAAI 2021 Human Detection and Segmentation via Multi-View Consensus ICCV 2021 Evaluating The Search Phase of Neural Architecture Search ICLR 2020 Domain Adaptive Multibranch Networks ICLR 2020 A Stochastic Conditioning Scheme for Diverse Human Motion Prediction CVPR 2020 DUNIT: Detection-Based Unsupervised Image-to-Image Translation CVPR 2020 Single-Stage 6D Object Pose Estimation CVPR 2020 Shape Reconstruction by Learning Differentiable Surface Representations CVPR 2020 ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture CVPR 2020 On the Loss Landscape of Adversarial Training: Identifying Challenges and How to Overcome Them NIPS 2020 Local Non-Rigid Structure-From-Motion From Diffeomorphic Mappings CVPR 2020 Indirect Local Attacks for Context-aware Semantic Segmentation Networks ECCV 2020 History Repeats Itself: Human Motion Prediction via Motion Attention ECCV 2020 Estimating People Flows to Better Count Them in Crowded Scenes ECCV 2020 ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks NIPS 2020 Volumetric Transformer Networks ECCV 2020 Segmentation-Driven 6D Object Pose Estimation CVPR 2019 Backpropagation-Friendly Eigendecomposition NIPS 2019 Learning Trajectory Dependencies for Human Motion Prediction ICCV 2019 GarNet: A Two-Stream Network for Fast and Accurate 3D Cloth Draping ICCV 2019 Overcoming Multi-model Forgetting ICML 2019 LEARNING FACTORIZED REPRESENTATIONS FOR OPEN-SET DOMAIN ADAPTATION ICLR 2019 Detecting the Unexpected via Image Resynthesis ICCV 2019 Neural Scene Decomposition for Multi-Person Motion Capture CVPR 2019 Context-Aware Crowd Counting CVPR 2019 Recurrent U-Net for Resource-Constrained Segmentation ICCV 2019 Geometry-Aware Deep Network for Single-Image Novel View Synthesis CVPR 2018 Learning Monocular 3D Human Pose Estimation From Multi-View Images CVPR 2018 Residual Parameter Transfer for Deep Domain Adaptation CVPR 2018 Learning to Find Good Correspondences CVPR 2018 Statistically-motivated Second-order Pooling ECCV 2018 Unsupervised Geometry-Aware Representation for 3D Human Pose Estimation ECCV 2018 Effective Use of Synthetic Data for Urban Scene Semantic Segmentation ECCV 2018 Eigendecomposition-free Training of Deep Networks with Zero Eigenvalue-based Losses ECCV 2018 Bringing Background Into the Foreground: Making All Classes Equal in Weakly-Supervised Video Semantic Segmentation ICCV 2017 Learning to Fuse 2D and 3D Image Cues for Monocular Body Pose Estimation ICCV 2017 Encouraging LSTMs to Anticipate Actions Very Early ICCV 2017 Joint Dimensionality Reduction and Metric Learning: A Geometric Take ICML 2017 Efficient Linear Programming for Dense CRFs CVPR 2017 Indoor Scene Parsing With Instance Segmentation, Semantic Labeling and Support Relationship Inference CVPR 2017 Boundary-Aware Instance Segmentation CVPR 2017 Compression-aware Training of Deep Networks NIPS 2017 Deep Subspace Clustering Networks NIPS 2017 Learning to Co-Generate Object Proposals With a Deep Structured Network CVPR 2016 Robust Multi-Body Feature Tracker: A Segmentation-Free Approach CVPR 2016 When VLAD Met Hilbert CVPR 2016 Memory Efficient Max Flow for Multi-Label Submodular MRFs CVPR 2016 Learning the Number of Neurons in Deep Networks NIPS 2016 Distribution-Matching Embedding for Visual Domain Adaptation JMLR 2016 Sample and Filter: Nonparametric Scene Parsing via Efficient Filtering CVPR 2016 Indoor Scene Structure Analysis for Single Image Depth Estimation CVPR 2015 Shape Interaction Matrix Revisited and Robustified: Efficient Subspace Clustering With Corrupted and Incomplete Data ICCV 2015 Riemannian Coding and Dictionary Learning: Kernels to the Rescue CVPR 2015 Iteratively Reweighted Graph Cut for Multi-Label MRFs With Non-Convex Priors CVPR 2015 Cutting Edge: Soft Correspondences in Multimodal Scene Parsing ICCV 2015 Deformable 3D Fusion: From Partial Dynamic 3D Observations to Complete 4D Models ICCV 2015 Structural Kernel Learning for Large Scale Multiclass Object Co-Detection ICCV 2015 Beyond Gauss: Image-Set Matching on the Riemannian Manifold of PDFs ICCV 2015 Domain Adaptation on the Statistical Manifold CVPR 2014 Discrete-Continuous Depth Estimation from a Single Image CVPR 2014 Optimizing Over Radial Kernels on Compact Manifolds CVPR 2014 Bregman Divergences for Infinite Dimensional Covariance Matrices CVPR 2014 Unsupervised Domain Adaptation by Domain Invariant Projection ICCV 2013 Continuous Inference in Graphical Models with Polynomial Energies CVPR 2013 Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices CVPR 2013 Mirror Surface Reconstruction from a Single Image CVPR 2013 Non-Linear Stationary Subspace Analysis with Application to Video Classification ICML 2013 A Framework for Shape Analysis via Hilbert Space Embedding ICCV 2013 A Family of MCMC Methods on Implicitly Defined Manifolds AISTATS 2012 Factorized Latent Spaces with Structured Sparsity NIPS 2010 Factorized Orthogonal Latent Spaces AISTATS 2010 Implicitly Constrained Gaussian Process Regression for Monocular Non-Rigid Pose Estimation NIPS 2010