activity
20242026
most citedMaskInversion: Localized Embeddings via Optimization of Explainability Maps

1 citations · 1 across the 2 of their papers we have counts for

collaborators

8 papers

cs.CV2026

Scene-Centric Unsupervised Video Panoptic Segmentation

Christoph Reich, Oliver Hahn, Nikita Araslanov +4

Video panoptic segmentation (VPS) aims to jointly detect, segment, and track all objects while partitioning the video into semantically consistent regions. We introduce the task se…

cs.CV20261 cited

MaskInversion: Localized Embeddings via Optimization of Explainability Maps

Walid Bousselham, Sofian Chaybouti, Christian Rupprecht +2

Vision-language foundation models such as CLIP have achieved tremendous results in global vision-language alignment, but still show some limitations in creating representations for…

cs.CV2026

FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views

Shangzhan Zhang, Jianyuan Wang, Yinghao Xu +5

We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images (i.e., as few as 2-8 inputs), which is a cha…

cs.CV2025

Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion

Aleksandar Jevtić, Christoph Reich, Felix Wimbauer +4

Semantic scene completion (SSC) aims to infer both the 3D geometry and semantics of a scene from single images. In contrast to prior work on SSC that heavily relies on expensive gr…

cs.CV2025

Scene-Centric Unsupervised Panoptic Segmentation

Oliver Hahn, Christoph Reich, Nikita Araslanov +3

Unsupervised panoptic segmentation aims to partition an image into semantically meaningful regions and distinct object instances without training on manually annotated data. In con…

cs.CV2025

AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos

Felix Wimbauer, Weirong Chen, Dominik Muhle +2

Estimating camera motion and intrinsics from casual videos is a core challenge in computer vision. Traditional bundle-adjustment based methods, such as SfM and SLAM, struggle to pe…