3 papers
cs.CV2026
CylinderDepth: Cylindrical Spatial Attention for Multi-View Consistent Self-Supervised Surround Depth Estimation
Samer Abualhanud, Christian Grannemann, Max Mehltretter
Self-supervised surround-view depth estimation enables dense, low-cost 3D perception with a 360° field of view from multiple minimally overlapping images. Yet, most existing metho…
cs.CV2026
Semantic Segmentation of Textured Non-manifold 3D Meshes using Transformers
Mohammadreza Heidarianbaei, Max Mehltretter, Franz Rottensteiner
Textured 3D meshes jointly represent geometry, topology, and appearance, yet their irregular structure poses significant challenges for deep-learning-based semantic segmentation. W…
cs.CV2026
Open-Vocabulary Semantic Segmentation in Remote Sensing via Hierarchical Attention Masking and Model Composition
Mohammadreza Heidarianbaei, Mareike Dorozynski, Hubert Kanyamahanga +2
In this paper, we propose ReSeg-CLIP, a new training-free Open-Vocabulary Semantic Segmentation method for remote sensing data. To compensate for the problems of vision language mo…