activity
20242026
collaborators

7 papers

cs.CV2026

Confidence matters: Leveraging Multi-view Geometric Priors for GS-based Reconstruction

Hongyu Zhou, Zorah Lähner

3D Gaussian splatting (3DGS) has emerged as a widely-used tool for novel view synthesis, offering real-time rendering in a sparse representation. However, the method's reliance on…

cs.GR2026

Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting

Hongyu Zhou, Zorah Lähner

After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface representation. However, extracting ac…

cs.GR2026

Laplace-Beltrami Operator for Gaussian Splatting

Hongyu Zhou, Zorah Lähner

With the rising popularity of 3D Gaussian splatting and the expanse of applications from rendering to 3D reconstruction, there comes also a need for geometry processing application…

cs.LG2026

Towards Improved Sentence Representations using Token Graphs

Krishna Sri Ipsit Mantri, Carola-Bibiane Schönlieb, Zorah Lähner +1

Obtaining a single-vector representation from a Large Language Model's (LLM) token-level outputs is a critical step for nearly all sentence-level tasks. However, standard pooling m…

cs.GR2025

MoAngelo: Motion-Aware Neural Surface Reconstruction for Dynamic Scenes

Mohamed Ebbed, Zorah Lähner

Dynamic scene reconstruction from multi-view videos remains a fundamental challenge in computer vision. While recent neural surface reconstruction methods have achieved remarkable…

cs.CV2025

Denoising Functional Maps: Diffusion Models for Shape Correspondence

Aleksei Zhuravlev, Zorah Lähner, Vladislav Golyanik

Estimating correspondences between pairs of deformable shapes remains a challenging problem. Despite substantial progress, existing methods lack broad generalization capabilities a…