← Back to all news
arXiv Computer Vision By Saurbh Singh Jamwal

Understanding Temporal Semantic Stability in Open-Vocabulary UAV Perception through Metric 3D Fusion

Read the original on arXiv Computer Vision →

The paper studies how open‑vocabulary segmentation models perform on UAV footage, focusing on temporal consistency of predictions. By linking frame‑wise outputs to persistent 3D voxels via metric fusion, the authors propose a voxel‑level evaluation that measures final agreement, Semantic Belief Drift, Observation Persistence, and uncertainty. Experiments on UAVid‑3D show that high overall agreement can mask instability when observations are sparse, and that persistence‑stratified analysis reveals greater disagreement for recurrent voxels while belief drift reduces with more evidence.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
1d ago

VoxelFix: Post-Hoc Semantic Correction of Completed 3D Voxel Maps

VoxelFix is a graph‑based post‑hoc semantic correction method that refines voxel labels in completed 3D voxel maps while preserving their geometry and occupancy. It learns to correct errors by exploiting local geometry and neighboring semantic information, using training pairs generated by corrupting annotated maps with class confusions from upstream perception pipelines. Experiments on OccuFly maps show consistent improvements of 4.23–5.00 percentage points in mIoU, especially for tree, roof, and wall classes, and the method generalizes to out‑of‑distribution aerial scenes.

By Sunesh Praveen Raja Sundarasami, Taehyoung Kim, Johannes Scherer, Toma\v{z} Coti\v{c}, Sivasubiramaniam Subbiah, Andreas Greiner, Paul Spannaus, Sebastian Houben
agentscomputer-visionrobotics
More like this →
arXiv Computer Vision
5d ago

Beyond Appearance: Can Multimodal Large Language Models Exploit Vertical Structure for Remote Sensing Natural Scene Understanding?

The paper introduces VertiCue-Bench, a diagnostic benchmark designed to test whether multimodal large language models (MLLMs) can perceive, ground, and utilize vertical structure information in remote-sensing natural scenes. It presents a three-stage framework—Perception, Grounding, Utilization—and a Representation Intervention Spectrum across various modalities to evaluate ten state-of-the-art models. The study finds a significant Vertical Structure Utilization Gap: while models show some geometric perception, they struggle to accurately link vertical evidence to spatial entities and incorporate it into semantic decisions.

By Jing Huang, Duanchu Wang, Junjie Yang, Zihang Cheng, Cheng Li, Lin Cui, Zhouyi Wu, Di Wang
llmsmultimodalbenchmarks
More like this →