Author

Holger Caesar

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Does the VGGT Family Need All Its Layers?

Which layers of a feed-forward geometry model are needed to preserve both camera poses and dense 3D structure? We study layer redundancy in VGGT, $\pi^3$, and VGGT-$\Omega$: 3,018 pruned configurations, scored on seven camera-pose and dense-geometry metrics across four indoor and outdoor datasets. Four findings follow:...

Feng-Yi Zhang, Holger Caesar, Xiang-Yu Sun et al. · 0 citations

Preprint Sep 2026

SplatLabel: Pseudo-Labelling through 4D Gaussian Splatting

While 2D Vision Foundation Models offer a pathway to automate 3D semantic pseudo-labelling, translating these priors into robust 3D representations typically requires complex heuristics or multi-model ensembles. We introduce SplatLabel, an automated pipeline that leverages a 4D Gaussian representation to extract LiDAR...

Nitya Nanvani, Andras Palffy, H. Caesar · 0 citations

#federated learning Preprint Oct 2026

FedCKA: Representation-Guided Layer Personalization for Federated 3D Perception Across Driving Domains

FedCKA is proposed, a Centered Kernel Alignment (CKA)-based strategy that dynamically handles the personalization-globalization trade-off, and outperforms established federated baselines, including FedBN, FedRep, and FedSelect, improving average NDS by 7 percentage points over the strongest baseline.

Jolle Verhoog, Ali Burak Ünal, Holger Caesar · 0 citations