4 citations · 18 across the 27 of their papers we have counts for
32 papers
Uncertainty-Aware RL-Controlled Adaptive 3D Mapping
Alpay Ozkan, Tunc Ozan Aydin, Marc Pollefeys +2
Voxel-based volumetric mapping is fundamental to 3D reconstruction, yet fixed-resolution grids remain inherently inefficient - wasting memory in uniform regions and losing detail i…
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…
AugSplat: Radiance Field-Informed Gaussian Splatting for Sparse-View Settings
Lorenzo Lazzaroni, Riccardo Bollati, Daniel Barath +2
Generating high-quality novel views at real-time frame rates remains a central challenge in 3D vision, particularly in sparse-view scenarios. Neural radiance fields have demonstrat…
SG2Loc: Sequential Visual Localization on 3D Scene Graphs
Nicole Damblon, Olga Vysotska, Federico Tombari +2
Visual localization in complex indoor environments remains a critical challenge for robotics and AR applications. Sequential localization, where pose estimates are refined over tim…
FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos
Alexandros Delitzas, Chenyangguang Zhang, Alexey Gavryushin +8
We present FunRec, a method for reconstructing functional 3D digital twins of indoor scenes directly from egocentric RGB-D interaction videos. Unlike existing methods on articulate…
OVI-MAP:Open-Vocabulary Instance-Semantic Mapping
Zilong Deng, Federico Tombari, Marc Pollefeys +2
Incremental open-vocabulary 3D instance-semantic mapping is essential for autonomous agents operating in complex everyday environments. However, it remains challenging due to the n…
VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM
Zihan Zhu, Wei Zhang, Moyang Li +3
We present VIGS-SLAM, a visual-inertial 3D Gaussian Splatting SLAM system that achieves robust real-time tracking and high-fidelity reconstruction. Although recent 3DGS-based SLAM…
SegSplat: Feed-forward Gaussian Splatting and Open-Set Semantic Segmentation
Peter Siegel, Federico Tombari, Marc Pollefeys +1
We have introduced SegSplat, a novel framework designed to bridge the gap between rapid, feed-forward 3D reconstruction and rich, open-vocabulary semantic understanding. By constru…
YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting
Botao Ye, Boqi Chen, Haofei Xu +2
Fast and flexible 3D scene reconstruction from unstructured image collections remains a significant challenge. We present YoNoSplat, a feedforward model that reconstructs high-qual…
HouseTour: A Virtual Real Estate A(I)gent
Ata Çelen, Marc Pollefeys, Daniel Barath +1
We introduce HouseTour, a method for spatially-aware 3D camera trajectory and natural language summary generation from a collection of images depicting an existing 3D space. Unlike…
ReSplat: Learning Recurrent Gaussian Splatting
Haofei Xu, Daniel Barath, Andreas Geiger +1
While existing feed-forward Gaussian splatting models offer computational efficiency and can generalize to sparse view settings, their performance is fundamentally constrained by r…
UnLoc: Leveraging Depth Uncertainties for Floorplan Localization
Matthias Wüest, Francis Engelmann, Ondrej Miksik +2
We propose UnLoc, an efficient data-driven solution for sequential camera localization within floorplans. Floorplan data is readily available, long-term persistent, and robust to c…
Object-X: Learning to Reconstruct Multi-Modal 3D Object Representations
Gaia Di Lorenzo, Federico Tombari, Marc Pollefeys +1
Learning effective multi-modal 3D representations of objects is essential for numerous applications, such as augmented reality and robotics. Existing methods often rely on task-spe…
Robust Human Registration with Body Part Segmentation on Noisy Point Clouds
Kai Lascheit, Daniel Barath, Marc Pollefeys +2
Registering human meshes to 3D point clouds is essential for applications such as augmented reality and human-robot interaction but often yields imprecise results due to noise and…
CrossOver: 3D Scene Cross-Modal Alignment
Sayan Deb Sarkar, Ondrej Miksik, Marc Pollefeys +2
Multi-modal 3D object understanding has gained significant attention, yet current approaches often assume complete data availability and rigid alignment across all modalities. We p…
DepthSplat: Connecting Gaussian Splatting and Depth
Haofei Xu, Songyou Peng, Fangjinhua Wang +4
Gaussian splatting and single-view depth estimation are typically studied in isolation. In this paper, we present DepthSplat to connect Gaussian splatting and depth estimation and…
Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information
Luca Di Giammarino, Boyang Sun, Giorgio Grisetti +3
Accurate localization in diverse environments is a fundamental challenge in computer vision and robotics. The task involves determining a sensor's precise position and orientation,…
Learning to Make Keypoints Sub-Pixel Accurate
Shinjeong Kim, Marc Pollefeys, Daniel Barath
This work addresses the challenge of sub-pixel accuracy in detecting 2D local features, a cornerstone problem in computer vision. Despite the advancements brought by neural network…
Global Structure-from-Motion Revisited
Linfei Pan, Dániel Baráth, Marc Pollefeys +1
Recovering 3D structure and camera motion from images has been a long-standing focus of computer vision research and is known as Structure-from-Motion (SfM). Solutions to this prob…
MAP-ADAPT: Real-Time Quality-Adaptive Semantic 3D Maps
Jianhao Zheng, Daniel Barath, Marc Pollefeys +1
Creating 3D semantic reconstructions of environments is fundamental to many applications, especially when related to autonomous agent operation (e.g., goal-oriented navigation or o…
"Where am I?" Scene Retrieval with Language
Jiaqi Chen, Daniel Barath, Iro Armeni +2
Natural language interfaces to embodied AI are becoming more ubiquitous in our daily lives. This opens up further opportunities for language-based interaction with embodied agents,…
Multiway Point Cloud Mosaicking with Diffusion and Global Optimization
Shengze Jin, Iro Armeni, Marc Pollefeys +1
We introduce a novel framework for multiway point cloud mosaicking (named Wednesday), designed to co-align sets of partially overlapping point clouds -- typically obtained from 3D…
Handbook on Leveraging Lines for Two-View Relative Pose Estimation
Petr Hruby, Shaohui Liu, Rémi Pautrat +2
We propose an approach for estimating the relative pose between calibrated image pairs by jointly exploiting points, lines, and their coincidences in a hybrid manner. We investigat…
Q-REG: End-to-End Trainable Point Cloud Registration with Surface Curvature
Shengze Jin, Daniel Barath, Marc Pollefeys +1
Point cloud registration has seen recent success with several learning-based methods that focus on correspondence matching and, as such, optimize only for this objective. Following…