Marc Pollefeys

VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation CVPR 2025 Relative Pose Estimation through Affine Corrections of Monocular Depth Priors CVPR 2025 R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization CVPR 2025 EgoPressure: A Dataset for Hand Pressure and Pose Estimation in Egocentric Vision CVPR 2025 CrossOver: 3D Scene Cross-Modal Alignment CVPR 2025 Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces CVPR 2025 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection ICCV 2025 ActLoc: Learning to Localize on the Move via Active Viewpoint Selection CORL 2025 FlowR: Flowing from Sparse to Dense 3D Reconstructions ICCV 2025 CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization ICCV 2025 Single-Scanline Relative Pose Estimation for Rolling Shutter Cameras ICCV 2025 SuperDec: 3D Scene Decomposition with Superquadrics Primitives ICCV 2025 Planar Affine Rectification from Local Change of Scale and Orientation ICCV 2025 Multi-View 3D Point Tracking ICCV 2025 Structure-from-Motion with a Non-Parametric Camera Model CVPR 2025 EgoM2P: Egocentric Multimodal Multitask Pretraining ICCV 2025 HouseTour: A Virtual Real Estate A(I)gent ICCV 2025 Benchmarking Egocentric Visual-Inertial SLAM at City Scale ICCV 2025 No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images ICLR 2025 ALSTER: A Local Spatio-Temporal Expert for Online 3D Semantic Reconstruction WACV 2025 CroCoDL: Cross-device Collaborative Dataset for Localization CVPR 2025 Learning to Filter Outlier Edges in Global SfM CVPR 2025 GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control CVPR 2025 ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding CVPR 2025 WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments CVPR 2025 MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion CVPR 2025 DepthSplat: Connecting Gaussian Splatting and Depth CVPR 2025 SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs ECCV 2024 Diffusion Bridges for 3D Point Cloud Denoising ECCV 2024 MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation ECCV 2024 MuRF: Multi-Baseline Radiance Fields CVPR 2024 SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes CVPR 2024 GLACE: Global Local Accelerated Coordinate Encoding CVPR 2024 Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning CVPR 2024 GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image CVPR 2024 EgoGen: An Egocentric Synthetic Data Generator CVPR 2024 F3Loc: Fusion and Filtering for Floorplan Localization CVPR 2024 UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections NIPS 2024 WildGaussians: 3D Gaussian Splatting In the Wild NIPS 2024 Dynamic 3D Gaussian Fields for Urban Areas NIPS 2024 Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation NIPS 2024 Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information ECCV 2024 Retrieval Robust to Object Motion Blur ECCV 2024 Learning to Make Keypoints Sub-Pixel Accurate ECCV 2024 StereoGlue: Joint Feature Matching and Robust Estimation ECCV 2024 Gravity-aligned Rotation Averaging with Circular Regression ECCV 2024 Global Structure-from-Motion Revisited ECCV 2024 Semicalibrated Relative Pose from an Affine Correspondence and Monodepth ECCV 2024 GeoCalib: Learning Single-image Calibration with Geometric Optimization ECCV 2024 MAP-ADAPT: Real-Time Quality-Adaptive Semantic 3D Maps ECCV 2024 Where am I? Scene Retrieval with Language ECCV 2024 Robust Incremental Structure-from-Motion with Hybrid Features ECCV 2024 Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels ECCV 2024 MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images ECCV 2024 WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation ECCV 2024 MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References ECCV 2024 LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry CVPR 2024 Multiway Point Cloud Mosaicking with Diffusion and Global Optimization CVPR 2024 Multi-Level Neural Scene Graphs for Dynamic Urban Environments CVPR 2024 Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion CVPR 2024 NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild CVPR 2024 3D Neural Edge Reconstruction CVPR 2024 Efficient Solution of Point-Line Absolute Pose CVPR 2024 SNI-SLAM: Semantic Neural Implicit SLAM CVPR 2024 ResFields: Residual Neural Fields for Spatiotemporal Signals ICLR 2024 RLSAC: Reinforcement Learning Enhanced Sample Consensus for End-to-End Robust Estimation ICCV 2023 HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World ICCV 2023 Human from Blur: Human Pose Tracking from Blurry Images ICCV 2023 Four-View Geometry With Unknown Radial Distortion CVPR 2023 SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding NIPS 2023 The Drunkard’s Odometry: Estimating Camera Motion in Deforming Scenes NIPS 2023 OpenMask3D: Open-Vocabulary 3D Instance Segmentation NIPS 2023 DeepLSD: Line Segment Detection and Refinement With Deep Image Gradients CVPR 2023 Removing Objects From Neural Radiance Fields CVPR 2023 VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction CVPR 2023 Privacy Preserving Localization via Coordinate Permutations ICCV 2023 Guiding Local Feature Matching with Surface Curvature ICCV 2023 OpenScene: 3D Scene Understanding With Open Vocabularies CVPR 2023 3D Line Mapping Revisited CVPR 2023 Tracking by 3D Model Estimation of Unknown Objects in Videos ICCV 2023 LightGlue: Local Feature Matching at Light Speed ICCV 2023 RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration ICCV 2023 R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras ICCV 2023 SGAligner: 3D Scene Alignment with Scene Graphs ICCV 2023 Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction ICCV 2023 GlueStick: Robust Image Matching by Sticking Points and Lines Together ICCV 2023 IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis ICCV 2023 CompNVS: Novel View Synthesis with Scene Completion ECCV 2022 NICE-SLAM: Neural Implicit Scalable Encoding for SLAM CVPR 2022 IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo CVPR 2022 Motion-From-Blur: 3D Shape and Motion Estimation of Motion-Blurred Objects in Videos CVPR 2022 Context-Aware Sequence Alignment Using 4D Skeletal Augmentation CVPR 2022 Camera Pose Estimation Using Implicit Distortion Models CVPR 2022 Privacy Preserving Partial Localization CVPR 2022 Learning To Align Sequential Actions in the Wild CVPR 2022 Learning To Find Good Models in RANSAC CVPR 2022 EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices ECCV 2022 LaMAR: Benchmarking Localization and Mapping for Augmented Reality ECCV 2022 NeFSAC: Neurally Filtered Minimal Samples ECCV 2022 Cross-Descriptor Visual Localization and Mapping ICCV 2021 Sat2Vid: Street-View Panoramic Video Synthesis From a Single Satellite Image ICCV 2021 Pixel-Perfect Structure-From-Motion With Featuremetric Refinement ICCV 2021 H2O: Two Hands Manipulating Objects for First Person Interaction Recognition ICCV 2021 Orthographic-Perspective Epipolar Geometry ICCV 2021 FMODetect: Robust Detection of Fast Moving Objects ICCV 2021 MBA-VO: Motion Blur Aware Visual Odometry ICCV 2021 NeuralFusion: Online Depth Fusion in Latent Space CVPR 2021 Back to the Feature: Learning Robust Camera Localization From Pixels To Pose CVPR 2021 DeepVideoMVS: Multi-View Stereo on Video With Recurrent Spatio-Temporal Fusion CVPR 2021 Privacy-Preserving Image Features via Adversarial Affine Subspace Embeddings CVPR 2021 Holistic 3D Scene Understanding From a Single Image With Implicit Representation CVPR 2021 SOLD2: Self-Supervised Occlusion-Aware Line Description and Detection CVPR 2021 PatchmatchNet: Learned Multi-View Patchmatch Stereo CVPR 2021 DeepSurfels: Learning Online Appearance Fusion CVPR 2021 Privacy Preserving Localization and Mapping From Uncalibrated Cameras CVPR 2021 DeFMO: Deblurring and Shape Recovery of Fast Moving Objects CVPR 2021 Shape As Points: A Differentiable Poisson Solver NIPS 2021 Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects NIPS 2021 Learning Motion Priors for 4D Human Body Capture in 3D Scenes ICCV 2021 Towards Efficient Graph Convolutional Networks for Point Cloud Handling ICCV 2021 Multi-View Optimization of Local Feature Geometry ECCV 2020 Online Invariance Selection for Local Feature Descriptors ECCV 2020 Convolutional Occupancy Networks ECCV 2020 Calibration-free Structure-from-Motion with Calibrated Radial Trifocal Tensors ECCV 2020 DIST: Rendering Deep Implicit Signed Distance Function With Differentiable Sphere Tracing CVPR 2020 Leveraging Photometric Consistency Over Time for Sparsely Supervised Hand-Object Reconstruction CVPR 2020 Why Having 10,000 Parameters in Your Camera Model Is Better Than Twelve CVPR 2020 Infrastructure-based Multi-Camera Calibration using Radial Projections ECCV 2020 Handcrafted Outlier Detection Revisited ECCV 2020 Geometry-Aware Satellite-to-Ground Image Synthesis for Urban Areas CVPR 2020 Deep Shutter Unrolling Network CVPR 2020 Self-Supervised Human Depth Estimation From Monocular Videos CVPR 2020 RoutedFusion: Learning Real-Time Depth Map Fusion CVPR 2020 Privacy Preserving Structure-from-Motion ECCV 2020 BAD SLAM: Bundle Adjusted Direct RGB-D SLAM CVPR 2019 Understanding the Limitations of CNN-Based Absolute Camera Pose Regression CVPR 2019 Episodic Curiosity through Reachability ICLR 2019 Reflection Separation using a Pair of Unpolarized and Polarized Images NIPS 2019 H+O: Unified Egocentric Recognition of 3D Hand-Object Poses and Interactions CVPR 2019 3D Instance Segmentation via Multi-Task Metric Learning ICCV 2019 Polarimetric Relative Pose Estimation ICCV 2019 Privacy Preserving Image Queries for Camera Localization ICCV 2019 Revisiting Radial Distortion Absolute Pose ICCV 2019 3D Appearance Super-Resolution With Deep Learning CVPR 2019 A Cross-Season Correspondence Dataset for Robust Semantic Segmentation CVPR 2019 D2-Net: A Trainable CNN for Joint Description and Detection of Local Features CVPR 2019 Hybrid Scene Compression for Visual Localization CVPR 2019 Privacy Preserving Image-Based Localization CVPR 2019 DeepLiDAR: Deep Surface Normal Guided Depth Prediction for Outdoor Scene From Sparse LiDAR Data and Single Color Image CVPR 2019 InLoc: Indoor Visual Localization With Dense Matching and View Synthesis CVPR 2018 A Dataset of Flash and Ambient Illumination Pairs from the Crowd ECCV 2018 Learning Priors for Semantic 3D Reconstruction ECCV 2018 Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching ECCV 2018 VSO: Visual Semantic Odometry ECCV 2018 Semantic Match Consistency for Long-Term Visual Localization ECCV 2018 Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions CVPR 2018 Consensus Maximization for Semantic Region Correspondences CVPR 2018 Semantic Visual Localization CVPR 2018 Augmenting Crowd-Sourced 3D Reconstructions Using Semantic Detections CVPR 2018 Hybrid Camera Pose Estimation CVPR 2018 Quad-Networks: Unsupervised Learning to Rank for Interest Point Detection CVPR 2017 Designing Effective Inter-Pixel Information Flow for Natural Image Matting CVPR 2017 Toroidal Constraints for Two-Point Localization Under High Outlier Ratios CVPR 2017 SGM-Nets: Semi-Global Matching With Neural Networks CVPR 2017 Comparative Evaluation of Hand-Crafted and Learned Local Features CVPR 2017 Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization? CVPR 2017 A Multi-View Stereo Benchmark With High-Resolution Images and Multi-Camera Videos CVPR 2017 From Point Clouds to Mesh Using Regression ICCV 2017 Semantically Informed Multiview Surface Refinement ICCV 2017 Matching neural paths: transfer from recognition to correspondence search NIPS 2017 Fast 3D Reconstruction of Faces With Glasses CVPR 2017 Consensus Maximization With Linear Matrix Inequality Constraints CVPR 2017 Semantic 3D Reconstruction With Continuous Regularization and Ray Potentials Using a Visibility Consistency Constraint CVPR 2016 Sparse to Dense 3D Reconstruction From Rolling Shutter Images CVPR 2016 Do It Yourself Hyperspectral Imaging With Everyday Digital Cameras CVPR 2016 Large-Scale Location Recognition and the Geometric Burstiness Problem CVPR 2016 TI-Pooling: Transformation-Invariant Pooling for Feature Learning in Convolutional Neural Networks CVPR 2016 Merging the Unmatchable: Stitching Visually Disconnected SfM Models ICCV 2015 Non-Parametric Structure-Based Calibration of Radially Symmetric Cameras ICCV 2015 Camera Pose Voting for Large-Scale Image-Based Localization ICCV 2015 Hyperpoints and Fine Vocabularies for Large-Scale Location Recognition ICCV 2015 Entropy Minimization for Convex Relaxation Approaches ICCV 2015 Optimizing the Viewing Graph for Structure-From-Motion ICCV 2015 Discrete Optimization of Ray Potentials for Semantic 3D Reconstruction CVPR 2015 Scalable Structure From Motion for Densely Sampled Videos CVPR 2015 Segment Based 3D Object Shape Priors CVPR 2015 Direction Matters: Depth Estimation With a Surface Normal Classifier CVPR 2015 Get Out of My Lab: Large-scale, Real-Time Visual-Inertial Localization RSS 2015 Turning Mobile Phones into 3D Scanners CVPR 2014 Efficient Structured Parsing of Facades Using Dynamic Programming CVPR 2014 Photometric Bundle Adjustment for Dense Multi-View 3D Modeling CVPR 2014 Class Specific 3D Object Shape Priors Using Surface Normals CVPR 2014 Relative Pose Estimation for a Multi-Camera System with Known Vertical Direction CVPR 2014 Pulling Things out of Perspective CVPR 2014 Globally Convergent Parallel MAP LP Relaxation Solver using the Frank-Wolfe Algorithm ICML 2014 Self-Calibration and Visual SLAM with a Multi-Camera System on a Micro Aerial Vehicle RSS 2014 Joint 3D Scene Reconstruction and Class Segmentation CVPR 2013 Articulated and Restricted Motion Subspaces and Their Signatures CVPR 2013 Radial Distortion Self-Calibration CVPR 2013 Rolling Shutter Stereo ICCV 2013 Automatic Registration of RGB-D Scans via Salient Directions ICCV 2013 Live Metric 3D Reconstruction on Mobile Phones ICCV 2013 City-Scale Change Detection in Cadastral 3D Models Using Images CVPR 2013 Motion Estimation for Self-Driving Cars with a Generalized Camera CVPR 2013 Box in the Box: Joint 3D Layout and Object Reasoning from Single Images ICCV 2013 Real-World Normal Map Capture for Nearly Flat Reflective Surfaces ICCV 2013 Globally Convergent Dual MAP LP Relaxation Solvers using Fenchel-Young Margins NIPS 2012 Gated Softmax Classification NIPS 2010