activity
20242026
collaborators

7 papers

cs.CV2026

Good Token Hunting: A Hitchhiker's Guide to Token Selection for Visual Geometry Transformers

Shuhong Zheng, Michael Oechsle, Erik Sandström +3

Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. Howe…

cs.CV2025

ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos

Shi Chen, Erik Sandström, Sandro Lombardi +2

Achieving truly practical dynamic 3D reconstruction requires online operation, global pose and map consistency, detailed appearance modeling, and the flexibility to handle both RGB…

cs.CV2024

LoopSplat: Loop Closure by Registering 3D Gaussian Splats

Liyuan Zhu, Yue Li, Erik Sandström +3

Simultaneous Localization and Mapping (SLAM) based on 3D Gaussian Splats (3DGS) has recently shown promise towards more accurate, dense 3D scene maps. However, existing 3DGS-based…

cs.CV2024

VF-NeRF: Learning Neural Vector Fields for Indoor Scene Reconstruction

Albert Gassol Puigjaner, Edoardo Mello Rella, Erik Sandström +2

Implicit surfaces via neural radiance fields (NeRF) have shown surprising accuracy in surface reconstruction. Despite their success in reconstructing richly textured surfaces, exis…

cs.CV2024

Loopy-SLAM: Dense Neural SLAM with Loop Closures

Lorenzo Liso, Erik Sandström, Vladimir Yugay +2

Neural RGBD SLAM techniques have shown promise in dense Simultaneous Localization And Mapping (SLAM), yet face challenges such as error accumulation during camera tracking resultin…

cs.CV2024

GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAM

Ganlin Zhang, Erik Sandström, Youmin Zhang +3

Recent advancements in RGB-only dense Simultaneous Localization and Mapping (SLAM) have predominantly utilized grid-based neural implicit encodings and/or struggle to efficiently r…