2 papers
cs.GR2026
TreeON: Reconstructing 3D Tree Point Clouds from Orthophotos and Heightmaps
Angeliki Grammatikaki, Johannes Eschner, Pedro Hermosilla +2
We present TreeON, a novel neural-based framework for reconstructing detailed 3D tree point clouds from sparse top-down geodata, using only a single orthophoto and its correspondin…
cs.HC2025
Interactive Discovery and Exploration of Visual Bias in Generative Text-to-Image Models
Johannes Eschner, Roberto Labadie-Tamayo, Matthias Zeppelzauer +1
Bias in generative Text-to-Image (T2I) models is a known issue, yet systematically analyzing such models' outputs to uncover it remains challenging. We introduce the Visual Bias Ex…