8 citations · 12 across the 30 of their papers we have counts for
37 papers
CLoSeR: Closing the Loop for Long-Context Streaming Reconstruction
Moyang Li, Zihan Zhu, Wei Zhang +2
Feedforward foundation models have recently shown remarkable 3D reconstruction capabilities. However, existing models exhibit large tracking drift in long-context streaming reconst…
RIGOR: Rig-Informed Geometry for Omnidirectional Reconstruction
Tingjun Huang, Dmitry Rudshin, Mathieu Meyer +3
Recent developments in feed-forward 3D reconstruction resulted in models which can recover dense scene representations and camera motion solely from an image stream. However, such…
OmniPoint: Universal Monocular Metric Pointcloud from Any Camera
Botao Ye, Marc Pollefeys, Ming-Hsuan Yang +1
Recovering metric 3D geometry from monocular images is a fundamental computer vision task, yet current methods remain heavily fragmented by fixed camera model assumptions and infle…
GenRec: Knowing Where to Reconstruct and Where to Generate
Ata Çelen, Jaewoo Jung, Federico Tombari +4
Generative novel view synthesis from sparse input images is rarely all reconstruction or all generation: pixels visible in some source view have a unique correct value modulated on…
Pixel-wise Planarity for High-Precision Monocular Plane Segmentation
Ahmetcan Yavuz, Alpay Ozkan, Rémi Pautrat +2
Plane segmentation from a single RGB image remains challenging due to imprecise region grouping and geometrically inconsistent supervision, often leading to over-segmentation and f…
Stable and Scalable Bundle Adjustment of Holistic 3D Structures
Shaohui Liu, Rémi Pautrat, Daniel Barath +3
Bundle Adjustment (BA) is a cornerstone of 3D computer vision and has benefited from decades of advances in sparse optimization and numerical methods. It was originally developed f…
Unified and Efficient Point-Line Local Features
François Costa, Raphael Kreft, Eckhard Goedeke +6
Multi-view computer vision pipelines typically rely on accurate sparse keypoints and robust descriptors. While incorporating line features has shown clear benefits for matching and…
PolyLayout: Multi-room Manhattan Layout Estimation
Gustav Hanning, Shaohui Liu, Rémi Pautrat +3
Estimating room layouts from multi-view imagery is a core task for indoor scene understanding. Existing methods are typically limited either by poor generalization to new datasets…
VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion
Zador Pataki, Paul-Edouard Sarlin, Marc Pollefeys
Accurately recovering the camera's calibration and metric poses for any unconstrained video would unlock large-scale training data for navigation and scene understanding. The domin…
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
Haofei Xu, Rundi Wu, Philipp Henzler +7
State-of-the-art single-image 3D reconstruction methods often rely on complex hybrid architectures and loss functions, or compress geometry into latent spaces in order to leverage…
ZipSplat: Fewer Gaussians, Better Splats
Alexander Veicht, Sunghwan Hong, Dániel Baráth +1
Feed-forward 3D Gaussian Splatting reconstructs scenes from images in seconds. Pixel-aligned methods keep every Gaussian grounded in an observation, but produce redundant, potentia…
Z-FLoc: Zero-Shot Floorplan Localization via Geometric Primitives
Ayumi Umemura, Toshinori Kuwahara, Marc Pollefeys +1
Visual localization -- estimating a camera pose within a pre-existing map -- is a fundamental problem in computer vision. Floorplans are an attractive map representation: they are…
Déjà View: Looping Transformers for Multi-View 3D Reconstruction
Alessandro Burzio, Tobias Fischer, Sven Elflein +9
Recent feed-forward 3D reconstruction transformers have scaled to over a billion parameters, following the broader trend of increasing model capacity in computer vision. Yet emergi…
Global Structure-from-Motion Meets Feedforward Reconstruction
Linfei Pan, Johannes Schönberger, Marc Pollefeys
Structure-from-Motion -- the process of simultaneously estimating camera poses and 3D scene structure from a collection of images -- remains a central challenge in computer vision,…
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
Weijie Wang, Zimu Li, Jinchuan Shi +5
Sparse-view 3D reconstruction is increasingly addressed with feed-forward splatting networks that predict explicit primitives directly from images. Yet most existing methods remain…
No Pose, No Problem in 4D: Feed-Forward Dynamic Gaussians from Unposed Multi-View Videos
Matteo Balice, Yanik Kunzi, Chenyangguang Zhang +4
Recent feed-forward 3D gaussian splatting methods have made dramatic progress on individual aspects of 3D scene reconstruction, but no existing method jointly addresses dynamic con…
Unblur-SLAM: Dense Neural SLAM for Blurry Inputs
Qi Zhang, Denis Rozumny, Francesco Girlanda +4
We propose Unblur-SLAM, a novel RGB SLAM pipeline for sharp 3D reconstruction from blurred image inputs. In contrast to previous work, our approach is able to handle different type…
DROID-SLAM in the Wild
Moyang Li, Zihan Zhu, Marc Pollefeys +1
We present a robust, real-time RGB SLAM system that handles dynamic environments by leveraging differentiable Uncertainty-aware Bundle Adjustment. Traditional SLAM methods typicall…
RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer
Jiuming Liu, Guangming Wang, Zhe Liu +7
Although point cloud registration has achieved remarkable advances in object-level and indoor scenes, large-scale LiDAR registration methods has been rarely explored before. Challe…
MegaFlow: Zero-Shot Large Displacement Optical Flow
Dingxi Zhang, Fangjinhua Wang, Marc Pollefeys +1
Accurate estimation of large displacement optical flow remains a critical challenge. Existing methods typically rely on iterative local search or/and domain-specific fine-tuning, w…
RaCo: Ranking and Covariance for Practical Learned Keypoints
Abhiram Shenoi, Philipp Lindenberger, Paul-Edouard Sarlin +1
This paper introduces RaCo, a lightweight neural network designed to learn robust and versatile keypoints suitable for a variety of 3D computer vision tasks. The model integrates t…
Scaling Image Geo-Localization to Continent Level
Philipp Lindenberger, Paul-Edouard Sarlin, Jan Hosang +4
Determining the precise geographic location of an image at a global scale remains an unsolved challenge. Standard image retrieval techniques are inefficient due to the sheer volume…
LightGlueStick: a Fast and Robust Glue for Joint Point-Line Matching
Aidyn Ubingazhibov, Rémi Pautrat, Iago Suárez +3
Lines and points are complementary local features, whose combination has proven effective for applications such as SLAM and Structure-from-Motion. The backbone of these pipelines a…
Benchmarking Egocentric Visual-Inertial SLAM at City Scale
Anusha Krishnan, Shaohui Liu, Paul-Edouard Sarlin +6
Precise 6-DoF simultaneous localization and mapping (SLAM) from onboard sensors is critical for wearable devices capturing egocentric data, which exhibits specific challenges, such…