activity
20192026
most citedSPARF: Neural Radiance Fields from Sparse and Noisy Poses

5 citations · 20 across the 13 of their papers we have counts for

collaborators

21 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

HouseLayout3D: A Benchmark and Training-Free Baseline for 3D Layout Estimation in the Wild

Valentin Bieri, Marie-Julie Rakotosaona, Keisuke Tateno +2

Current 3D layout estimation models are primarily trained on synthetic datasets containing simple single room or single floor environments. As a consequence, they cannot natively h…

cs.CV2025

Learning Neural Exposure Fields for View Synthesis

Michael Niemeyer, Fabian Manhardt, Marie-Julie Rakotosaona +5

Recent advances in neural scene representations have led to unprecedented quality in 3D reconstruction and view synthesis. Despite achieving high-quality results for common benchma…

cs.CV2025

AnyUp: Universal Feature Upsampling

Thomas Wimmer, Prune Truong, Marie-Julie Rakotosaona +4

We introduce AnyUp, a method for feature upsampling that can be applied to any vision feature at any resolution, without encoder-specific training. Existing learning-based upsample…

cs.CV2025

Masks make discriminative models great again!

Tianshi Cao, Marie-Julie Rakotosaona, Ben Poole +2

We present Image2GS, a novel approach that addresses the challenging problem of reconstructing photorealistic 3D scenes from a single image by focusing specifically on the image-to…

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…