Computer Vision and Geometry Group

Stereoglue: Robust estimation with single-point solvers

Conference: ECCV 2024

Authors: Daniel Barath , Dmytro Mishkin , Luca Cavalli , Paul-Edouard Sarlin , Petr Hruby , Marc Pollefeys

Paper

Semicalibrated Relative Pose from an Affine Correspondence and Monodepth

Conference: ECCV 2024

Authors: Petr Hruby , Marc Pollefeys , Daniel Barath

Paper

Diffusion Bridges for 3D Point Cloud Denoising

Conference: ECCV 2024

Authors: Mathias Vogel Hüni , Keisuke Tateno , Marc Pollefeys , Federico Tombari , Marie-Julie Rakotosaona , Francis Engelmann

Paper

SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs

Conference: ECCV 2024

Authors: Yang Miao , Francis Engelamann , Olga Vysotksa , Federico Tombari , Marc Pollefeys , Daniel Barath

Paper

MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References

Conference: ECCV 2024

Authors: Lukas Böliger , Mihai Dusmanu , Marc Pollefeys , Zuria Bauer

Paper

WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation

Conference: ECCV 2024

Authors: Tianjian Jiang , Johsan Billingham , Sebastian Müksch , Juan Zarate , Nicolas Evans , Martin Oswald , Otmar Hilliges , Manuel Kaufmann , Jie Song

Paper

MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

Conference: ECCV 2024

Authors: Yuedong Chen , Haofei Xu , Chuanxia Zheng , Bohan Zhuang , Marc Pollefeys , Andreas Geiger , Tat-Jen Cham , Jianfei Cai

Paper

Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels

Conference: ECCV 2024

Authors: Rui Huang , Songyou Peng , Ayca Takmaz , Federico Tombari , Marc Pollefeys , Shiji Song , Gao Huang , Francis Engelmann

Paper

Robust Incremental Structure-from-Motion with Hybrid Features

Conference: ECCV 2024

Authors: Shaohui Liu , Yidan Gao , Tianyi Zhang , Remi Pautrat , Johannes Schönberger , Viktor Larsson , Marc Pollefeys

Paper

"Where am I?" Scene Retrieval with Language

Conference: ECCV 2024

Authors: Jiaqi Chen , Daniel Barath , Iro Armeni , Marc Pollefeys , Hermann Blum

Paper

MAP-ADAPT: Real-Time Quality-Adaptive Semantic 3D Maps

Conference: ECCV 2024

Authors: Jianhao Zheng , Daniel Barath , Marc Pollefeys , Iro Armeni

Paper

MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation

Conference: ECCV 2024

Authors: Linyan Yang , Lukas Hoyer , Mark Weber , Tobias Fischer , Dengxin Dai , Laura Leal-Taixe , Daniel Cremers , Marc Pollefeys , Luc Van Gool

Paper

GeoCalib: Learning Single-image Calibration with Geometric Optimization

Conference: ECCV 2024

Authors: Alexander Veicht , Paul-Edouard Sarlin , Philipp Lindenberger , Marc Pollefeys

Paper

Global Structure-from-Motion Revisited

Conference: ECCV 2024

Authors: Linfei Pan , Johannes Schönberger , Daniel Barath , Marc Pollefeys

Paper

Gravity-aligned Rotation Averaging with Circular Regression

Conference: ECCV 2024

Authors: Linfei Pan , Marc Pollefeys , Daniel Barath

Paper

Learning to Find Sub-Pixel Accurate Keypoints

Conference: ECCV 2024

Authors: Shinjeong Kim , Marc Pollefeys , Daniel Barath

Paper

Retrieval Robust to Object Motion Blur

Conference: ECCV 2024

Authors: Rong Zhou , Marc Pollefeys , Denys Rozumnyi

Paper

Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information

Conference: ECCV 2024

Authors: Luca Di Giammarino , Boyang Sun , Marc Pollefeys , Giorgio Grisetti , Hermann Blum , Daniel Barath

Paper

Volumetric Semantically Consistent 3D Panoptic Mapping

Conference: IROS 2024

Authors: Miao Yang , Iro Armeni , Marc Pollefeys , Daniel Barath

Paper

CR3DT: Camera-RADAR Fusion for 3D Detection and Tracking

Conference: IROS 2024

Authors: Jonas Kühne , Nicolas Baumann , Michael Baumgartner , Ghignone Edoardo , Tobias Fischer , Yung-Hsu Yang , Marc Pollefeys , Michele Magno

Paper

PickScan: Object discovery and reconstruction from handheld interactions

Conference: IROS 2024

Authors: Vincent Van der Brugge , Marc Pollefeys , Joshua B. Tenenbaum , Ayush Tewari , Krishna Murthy Jatavallabhula

Paper

LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

Conference: CVPR 2024

Authors: Weirong Chen , Le Chen , Rui Wang , Marc Pollefeys

Paper

MuRF: Multi-Baseline Radiance Fields

Conference: CVPR 2024

Authors: Haofei Xu , Anpei Chen , Yuedong Chen , Christos Sakaridis , Yulun Zhang , Marc Pollefeys , Andreas Geiger , Fisher Yu

Paper

Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning

Conference: CVPR 2024

Authors: Rui Li , Tobias Fischer , Mattia Segu , Marc Pollefeys , Luc Van Gool , Federico Tombari

Paper

Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion

Conference: CVPR 2024

Authors: Zuoyue Li , Zhenqiang Li , Zhaopeng Cui , Marc Pollefeys , Martin R. Oswald

Paper

Multiway Point Cloud Mosaicking with Diffusion and Global Optimization

Conference: CVPR 2024

Authors: Shengze Jin , Iro Armeni , Marc Pollefeys , Daniel Barath

Paper

Multi-Level Neural Scene Graphs for Dynamic Urban Environments

Conference: CVPR 2024

Authors: Tobias Fischer , Lorenzo Porzi , Samuel Rota Bulò , Marc Pollefeys , Peter Kontschieder

Paper

SNI-SLAM: Semantic Neural Implicit SLAM

Conference: CVPR 2024

Authors: Siting Zhu , Guangming Wang , Hermann Blum , Jiuming Liu , LiangSong , Marc Pollefeys , Hesheng Wang

Paper

3D Neural Edge Reconstruction

Conference: CVPR 2024

Authors: Lei Li , Songyou Peng , Zehao Yu , Shaohui Liu , Rémi Pautrat , Xiaochuan Yin , Marc Pollefeys

Paper

EgoGen: An Egocentric Synthetic Data Generator

Conference: CVPR 2024

Authors: Gen Li , Kaifeng Zhao , Siwei Zhang , Xiaozhong Lyu , Mihai Dusmanu , Yan Zhang , Marc Pollefeys , Siyu Tang

Paper

GLACE: Global Local Accelerated Coordinate Encoding

Conference: CVPR 2024

Authors: Fangjinhua Wang , Xudong Jiang , Silvano Galliani , Christoph Vogel , Marc Pollefeys

Paper

F^3Loc: Fusion and Filtering for Floorplan Localization

Conference: CVPR 2024

Authors: Changan Chen , Rui Wang , Christoph Vogel , Marc Pollefeys

Paper

NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild

Conference: CVPR 2024

Authors: Weining Ren , Zihan Zhu , Boyang Sun , Jiaqi Chen , Marc Pollefeys , Songyou Peng

Paper

GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image

Conference: CVPR 2024

Authors: Chong Bao , Yinda Zhang , Yuan Li , Xiyu Zhang , Bangbang Yang , Hujun Bao , Marc Pollefeys , Guofeng Zhang , Zhaopeng Cui

Paper

Absolute Pose from One or Two Scaled and Oriented Features

Conference: CVPR 2024

Authors: Jonathan Ventura , Zuzana Kukelova , Torsten Sattler , Daniel Barath

Paper

DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching

Conference: CVPR 2024

Authors: Shuzhe Wang , Juho Kannala , Daniel Barath

Paper

Efficient Solution of Point-Line Absolute Pose

Conference: CVPR 2024

Authors: Petr Hruby , Timothy Duff , Marc Pollefeys

Paper

SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes

Conference: CVPR 2024 (Oral)

Authors: Alexandros Delitzas , Ayca Takmaz , Federico Tombari , Robert Sumner , Marc Pollefeys , Francis Engelmann

Project

Paper

Handbook on Leveraging Lines for Two-View Relative Pose Estimation

Conference: 3DV 2024

Authors: Petr Hruby , Shaohui Liu , Rémi Pautrat , Marc Pollefeys , Daniel Barath

Paper

Q-REG: End-to-End Trainable Point Cloud Registration with Surface Curvature

Conference: 3DV 2024

Authors: Shengze Jin , Daniel Barath , Marc Pollefeys , Iro Armeni

Paper

NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM

Conference: 3DV 2024 (Oral, Best Paper Honorable Mention)

Authors: Zihan Zhu* , Songyou Peng* , Viktor Larsson , Zhaopeng Cui , Martin R. Oswald , Andreas Geiger , Marc Pollefeys

Paper

LabelMaker: Automatic Semantic Label Generation from RGB-D

Conference: 3DV 2024

Authors: Silvan Weder , Hermann Blum , Francis Engelmann , Marc Pollefeys

Project

Paper

Code

OpenMask3D: Open-Vocabulary 3D Instance Segmentation

Conference: NeurIPS 2023

Authors: Ayca Takmaz , Elisabetta Fedele , Robert Sumner , Marc Pollefeys , Federico Tombari , Francis Engelmann

Project

Paper

Code

3D Segmentation of Humans in Point Clouds with Synthetic Data

Conference: ICCV 2023

Authors: Ayça Takmaz , Jonas Schult , Irem Kaftan , Mertcan Akçay , Bastian Leibe , Robert Sumner , Francis Engelmann , Siyu Tang

Project

Paper

Code

Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries

Conference: CVPR 2023

Authors: Yuanwen Yue , Theodora Kontogianni , Konrad Schindler , Francis Engelmann

Project

Paper

Code

Mask3D: Mask Transformer for 3D Semantic Instance Segmentation

Conference: ICRA 2023

Authors: Jonas Schult , Francis Engelmann , Alexander Hermans , Or Litany , Siyu Tang , Bastian Leibe

Project

Paper

Code

Privacy Preserving Localization via Coordinate Permutations

Conference: ICCV 2023

Authors: Linfei Pan , Johannes L. Schönberger , Viktor Larsson , Marc Pollefeys

Project

Paper

OpenScene: 3D Scene Understanding with Open Vocabularies

Conference: CVPR 2023

Authors: Songyou Peng , Kyle Genova , Chiyu ''Max'' Jiang , Andrea Tagliasacchi , Marc Pollefeys , Thomas Funkhouser

Project

Paper

Code

GlueStick: Robust Image Matching by Sticking Points and Lines Together

Conference: ICCV 2023

Authors: Rémi Pautrat , Iago Suárez , Yifan Yu , Marc Pollefeys , Viktor Larsson

Project

Paper

Code

Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction

Conference: ICCV 2023

Authors: Rémi Pautrat , Shaohui Liu , Petr Hruby , Marc Pollefeys , Daniel Barath

Project

Paper

Code

3D Line Mapping Revisited

Conference: CVPR 2023 (Highlight)

Authors: Shaohui Liu , Yifan Yu , Rémi Pautrat , Marc Pollefeys , Viktor Larsson

Project

Paper

Code

DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients

Conference: CVPR 2023

Authors: Rémi Pautrat , Dániel Béla Baráth , Viktor Larsson , Martin R. Oswald , Marc Pollefeys

Project

Paper

Code

Four-view Geometry with Unknown Radial Distortion

Conference: CVPR 2023

Authors: Petr Hruby , Viktor Korotynskiy , Timothy Duff , Marc Pollefeys , Tomas Pajdla , Viktor Larsson

Paper

Code

VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction

Conference: CVPR 2023

Authors: Yufan Ren , Fangjinhua Wang , Tong Zhang , Marc Pollefeys , Sabine Süsstrunk

Project

Paper

Code

SGAligner: 3D Scene Alignment with Scene Graphs

Conference: ICCV 2023

Authors: S. D. Sarkar , O. Miksik , M. Pollefeys , D. Barath , I. Armeni

Project

Paper

Code

Guiding Local Feature Matching with Surface Curvature

Conference: ICCV 2023

Authors: S. D. Sarkar , O. Miksik , M. Pollefeys , D. Barath , I. Armeni

Paper

Code

Adaptive Reordering Sampler with Neurally Guided MAGSAC

Conference: ICCV 2023

Authors: T. Wei , J. Matas , D. Barath

Paper

Code

Fast Globally Optimal Surface Normal Estimation from an Affine Correspondence

Conference: ICCV 2023

Authors:

Project

Paper

Generalized Differentiable RANSAC

Conference: ICCV 2023

Authors: L. Hajder , L. Lóczi , D. Barath

Paper

Code

P1AC: Revisiting absolute pose from a single affine correspondence

Conference: ICCV 2023 (oral)

Authors: J. Ventura , Z. Kukelova , T. Sattler , D. Barath

Paper

Code

Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes

Conference: ECCV 2022 (Oral)

Authors: Julian Chibane , Francis Engelmann , Tuan Anh Tran , Gerard Pons-Moll

Project

Paper

Code

Camera Pose Estimation using Implicit Distortion Models

Conference: CVPR 2022

Authors: Linfei Pan , Marc Pollefeys , Viktor Larsson

Project

Paper

Code

NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Conference: CVPR 2022

Authors: Zihan Zhu* , Songyou Peng* , Viktor Larsson , Weiwei Xu , Hujun Bao , Zhaopeng Cui , Martin R. Oswald , Marc Pollefeys

Project

Paper

Code

Learning to Solve Hard Minimal Problems

Conference: CVPR 2022 (Best Paper Award)

Authors: Petr Hruby , Timothy Duff , Anton Leykin , Tomas Pajdla

Paper

Code

IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo

Conference: CVPR 2022

Authors: Fangjinhua Wang , Silvano Galliani , Christoph Vogel , Marc Pollefeys

Paper

Code

Mix3D: Out-of-Context Data Augmentation for 3D Scenes

Conference: 3DV 2021

Authors: Alexey Nekrasov , Jonas Schult , Or Litany , Bastian Leibe , Francis Engelmann

Paper

Code

Shape As Points: A Differentiable Poisson Solver

Conference: NeurIPS 2021 (Oral, top 0.6%)

Authors: Songyou Peng , Chiyu 'Max' Jiang , Yiyi Liao , Michael Niemeyer , Marc Pollefeys , Andreas Geiger

Project

Paper

Code

SOLD²: Self-supervised Occlusion-aware Line Description and Detection

Conference: CVPR 2021

Authors: Rémi Pautrat , Juan-Ting Lin , Viktor Larsson , Martin R. Oswald , Marc Pollefeys

Project

Paper

Code

PatchmatchNet: Learned Multi-View Patchmatch Stereo

Conference: 2021 (Oral)

Authors: Fangjinhua Wang , Silvano Galliani , Christoph Vogel , Pablo Speciale , Marc Pollefeys

Paper

Code

Compression and Completion of Animated Point Clouds using Topological Properties of the Manifold

Conference: 3DV 2020

Authors: Linfei Pan , Ľubor Ladický , Marc Pollefeys

Project

Paper

Convolutional Occupancy Networks

Conference: ECCV 2020 (Spotlight, top 5%)

Authors: Songyou Peng , Michael Niemeyer , Lars Mescheder , Marc Pollefeys , Andreas Geiger

Project

Paper

Code

Online Invariance Selection for Local Feature Descriptors

Conference: ECCV 2020

Authors: Rémi Pautrat , Viktor Larsson , Martin R. Oswald , Marc Pollefeys

Project

Paper

Code

Crowd-Guided Ensembles: How Can We Choreograph Crowd Workers for Video Segmentation?

Conference: ACM CHI 2018

Authors: Alexandre Kaspar , Genevieve Patterson , Changil Kim , Yagiz Aksoy , Wojciech Matusik , Mohamed Elgharib

Paper

Designing Effective Inter-Pixel Information Flow for Natural Image Matting

Conference: CVPR 2017

Authors: Yagiz Aksoy , Aydin Tunc Ozan , Marc Pollefeys

Project

Paper

Code

Semantic Multi-view Stereo: Jointly Estimating Objects and Voxels

Conference: CVPR 2017

Authors: Ali Osman Ulusoy , Michael Black , Andreas Geiger

Project

Paper

Code

Bounding Boxes, Segmentations and Object Coordinates: How Important is Recognition for 3D Scene Flow Estimation in Autonomous Driving Scenarios?

Conference: ICCV 2017

Authors: Aseem Behl , Omid Hosseini Jafari , Siva Karthik Mustikovela , Hassan Abu Alhaija , Carsten Rother , Andreas Geiger

Project

Paper

Code

An Exploration of 2D and 3D Deep Learning Techniques for Cardiac MR Image Segmentation

Conference: International Workshop on Statistical Atlases and Computational Modelling of the Heart 2017

Authors: Christian F. Baumgartner , Lisa M. Koch , Marc Pollefeys , Ender Konukoglu

Project

Paper

Code

Toroidal Constraints for Two Point Localization Under High Outlier Ratios

Conference: CVPR 2017

Authors: Federico Camposeco , Torsten Sattler , Andrea Cohen , Andreas Geiger , Marc Pollefeys

Project

Paper

Code

OctNet: Learning Deep 3D Representations at High Resolutions

Conference: CVPR 2017

Authors: Gernot Riegler , Ali Osman Ulusoy , Andreas Geiger

Project

Paper

Code

OctNetFusion: Learning Depth Fusion from Data

Conference: 3DV 2017

Authors: Gernot Riegler , Ali Osman Ulusoy , Horst Bischof , Andreas Geiger

Project

Paper

Code

Augmented Reality Meets Deep Learning for Car Instance Segmentation in Urban Scenes

Conference: BMVC 2017

Authors: Hassan Abu Alhaija , Siva Karthik Mustikovela , Lars Mescheder , Andreas Geiger , Carsten Rother

Project

Paper

Code

Mapping on the Fly: Real-time 3D Dense Reconstruction, Digital Surface Map and Incremental Orthomosaic Generation for Unmanned Aerial Vehicles

Conference: International Conference Field and Service Robotics 2017

Authors: Timo Hinzmann , Johannes Lutz Schonberger , Marc Pollefeys , Roland Siegwart

Project

Paper

Code

Slow Flow: Exploiting High-Speed Cameras for Accurate and Diverse Optical Flow Reference Data

Conference: CVPR 2017

Authors: Joel Janai , Fatma Güney , Jonas Wulff , Michael Black , Andreas Geiger

Project

Paper

Code

Sparsity Invariant CNNs

Conference: 3DV 2017

Authors: Jonas Uhrig , Nick Schneider , Lukas Schneider , Uwe Franke , Thomas Brox , Andreas Geiger

Project

Paper

Code

Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks

Conference: ICML 2017

Authors: Lars Mescheder , Sebastian Nowozin , Andreas Geiger

Project

Paper

Code

The Numerics of GANs

Conference: NIPS 2017

Authors: Lars Mescheder , Sebastian Nowozin , Andreas Geiger

Project

Paper

Code

Semantically Informed Multiview Surface Refinement

Conference: ICCV 2017

Authors: M. Blaha , M. Rothermel , M. R. Oswald , T. Sattler , A. Richard , J. D. Wegner , M. Pollefeys , K. Schindler

Project

Paper

Code

AR Museum: A Mobile Augmented Reality Application for Interactive Painting Recoloring

Conference: International Conference on Game and Entertainment Technologies 2017

Authors: Mattia Ryffel , Fabio Zund , Yagiz Aksoy , Alessia Marra , Maurizio Nitti , Tunc Ozan Aydin , Bob Sumner

Project

Paper

Code

Quad-Networks: Unsupervised Learning to Rank for Interest Point Detection

Conference: CVPR 2017

Authors: N. Savinov , A. Seki , L. Ladicky , T. Sattler , Marc Pollefeys

Project

Paper

Code

Consensus Maximization with Linear Matrix Inequality Constraints

Conference: CVPR 2017

Authors: Pablo Speciale , Danda P. Paudel , Martin R. Oswald , Till Kroeger , Luc V. Gool , Marc Pollefeys

Project

Paper

Code

Direct Visual Odometry for a Fisheye-Stereo Camera

Conference: IROS 2017

Authors: Peidong Liu , Lionel Heng , Torsten Sattler , Andreas Geiger , Marc Pollefeys

Project

Paper

Code

Comparative Evaluation of Hand-Crafted and Learned Local Features

Conference: CVPR 2017

Authors: Johannes Lutz Schonberger , Hans Hardmeier , Torsten Sattler , Marc Pollefeys

Project

Paper

Code

Publication

2024

Stereoglue: Robust estimation with single-point solvers

Semicalibrated Relative Pose from an Affine Correspondence and Monodepth

Diffusion Bridges for 3D Point Cloud Denoising

SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs

MaRINeR: Enhancing Novel Views by Matching Rendered Images with Nearby References

WorldPose: A World Cup Dataset for Global 3D Human Pose Estimation

MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels

Robust Incremental Structure-from-Motion with Hybrid Features

"Where am I?" Scene Retrieval with Language

MAP-ADAPT: Real-Time Quality-Adaptive Semantic 3D Maps

MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation

GeoCalib: Learning Single-image Calibration with Geometric Optimization

Global Structure-from-Motion Revisited

Gravity-aligned Rotation Averaging with Circular Regression

Learning to Find Sub-Pixel Accurate Keypoints

Retrieval Robust to Object Motion Blur

Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information

Volumetric Semantically Consistent 3D Panoptic Mapping

CR3DT: Camera-RADAR Fusion for 3D Detection and Tracking

PickScan: Object discovery and reconstruction from handheld interactions

LEAP-VO: Long-term Effective Any Point Tracking for Visual Odometry

MuRF: Multi-Baseline Radiance Fields

Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning

Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion

Multiway Point Cloud Mosaicking with Diffusion and Global Optimization

Multi-Level Neural Scene Graphs for Dynamic Urban Environments

SNI-SLAM: Semantic Neural Implicit SLAM

3D Neural Edge Reconstruction

EgoGen: An Egocentric Synthetic Data Generator

GLACE: Global Local Accelerated Coordinate Encoding

F^3Loc: Fusion and Filtering for Floorplan Localization

NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild

GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image

Absolute Pose from One or Two Scaled and Oriented Features

DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching

Efficient Solution of Point-Line Absolute Pose

SceneFun3D: Fine-Grained Functionality and Affordance Understanding in 3D Scenes

Handbook on Leveraging Lines for Two-View Relative Pose Estimation

Q-REG: End-to-End Trainable Point Cloud Registration with Surface Curvature

NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM

LabelMaker: Automatic Semantic Label Generation from RGB-D

2023

OpenMask3D: Open-Vocabulary 3D Instance Segmentation

3D Segmentation of Humans in Point Clouds with Synthetic Data

Connecting the Dots: Floorplan Reconstruction Using Two-Level Queries

Mask3D: Mask Transformer for 3D Semantic Instance Segmentation

Privacy Preserving Localization via Coordinate Permutations

OpenScene: 3D Scene Understanding with Open Vocabularies

GlueStick: Robust Image Matching by Sticking Points and Lines Together

Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction

3D Line Mapping Revisited

DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients

Four-view Geometry with Unknown Radial Distortion

VolRecon: Volume Rendering of Signed Ray Distance Functions for Generalizable Multi-View Reconstruction

SGAligner: 3D Scene Alignment with Scene Graphs

Guiding Local Feature Matching with Surface Curvature

Adaptive Reordering Sampler with Neurally Guided MAGSAC

Fast Globally Optimal Surface Normal Estimation from an Affine Correspondence

Generalized Differentiable RANSAC

P1AC: Revisiting absolute pose from a single affine correspondence

2022

Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes

Camera Pose Estimation using Implicit Distortion Models

NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Learning to Solve Hard Minimal Problems

IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo

2021

Mix3D: Out-of-Context Data Augmentation for 3D Scenes

Shape As Points: A Differentiable Poisson Solver

SOLD²: Self-supervised Occlusion-aware Line Description and Detection

PatchmatchNet: Learned Multi-View Patchmatch Stereo

2020

Compression and Completion of Animated Point Clouds using Topological Properties of the Manifold

Convolutional Occupancy Networks

Online Invariance Selection for Local Feature Descriptors

2018

Crowd-Guided Ensembles: How Can We Choreograph Crowd Workers for Video Segmentation?