collaborators

6 papers

cs.CV2026

Remove360: Benchmarking Residuals After Object Removal in 3D Gaussian Splatting

Simona Kocour, Assia Benbihi, Torsten Sattler

An object can disappear from a 3D scene, yet still be detectable. Even after visual removal, modern vision models may infer what was originally present. In this work, we introduce…

cs.RO2026

Benchmarking the Effects of Object Pose Estimation and Reconstruction on Robotic Grasping Success

Varun Burde, Pavel Burget, Torsten Sattler

3D reconstruction serves as the foundational layer for numerous robotic perception tasks, including 6D object pose estimation and grasp pose generation. Modern 3D reconstruction me…

cs.CV2025

LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering

Jonas Kulhanek, Marie-Julie Rakotosaona, Fabian Manhardt +5

In this work, we present a novel level-of-detail (LOD) method for 3D Gaussian Splatting that enables real-time rendering of large-scale scenes on memory-constrained devices. Our ap…

cs.CV2025

Large-scale visual SLAM for in-the-wild videos

Shuo Sun, Torsten Sattler, Malcolm Mielle +2

Accurate and robust 3D scene reconstruction from casual, in-the-wild videos can significantly simplify robot deployment to new environments. However, reliable camera pose estimatio…

cs.CV2025

Is there anything left? Measuring semantic residuals of objects removed from 3D Gaussian Splatting

Simona Kocour, Assia Benbihi, Aikaterini Adam +1

Searching in and editing 3D scenes has become extremely intuitive with trainable scene representations that allow linking human concepts to elements in the scene. These operations…

cs.CV2025

EdgeGaussians -- 3D Edge Mapping via Gaussian Splatting

Kunal Chelani, Assia Benbihi, Torsten Sattler +1

With their meaningful geometry and their omnipresence in the 3D world, edges are extremely useful primitives in computer vision. 3D edges comprise of lines and curves, and methods…