The paper introduces a saliency-depth conditioning approach for zero‑shot segmentation of communication‑tower components in cluttered UAV imagery. By combining appearance‑based saliency with monocular relative depth, the method creates a coarse tower prior that suppresses irrelevant background, and integrates this module with Grounded‑SAM and SAM 3 to produce SD‑Grounded‑SAM and SD‑SAM 3. Experiments on the TOW‑300 dataset show that SD‑SAM 3 achieves the best instance‑segmentation performance while SD‑Grounded‑SAM reduces false positives, with ablations confirming the complementary benefits of saliency, depth, and box refinement.
arXiv:2608.22289v1 Announce Type: new Abstract: Unmanned aerial vehicles (UAVs) increasingly require robust visual localization in GNSS-denied environments. A common solution estimates UAV poses by m...
arXiv:2608.29626v1 Announce Type: new Abstract: Salient object detection in optical remote sensing images (ORSI-SOD) requires dense predictions that preserve object completeness and structural contin...
arXiv:2608. 09270v1 Announce Type: cross Abstract: Fine-grained cross-modal understanding in drone views is essential for aerial vision-language navigation.
SAM‑V is a geometry‑aware extension of the Segment Anything Model (SAM) that integrates 3D priors from a feed‑forward geometry model (VGGT) into 2D segmentation. It uses a prompt‑fusion mechanism to combine sparse SAM prompts with view‑specific camera tokens and local VGGT features, enabling a mask decoder that attends to both dense 2D and 3D cues. The resulting end‑to‑end system produces consistent multi‑view instance segmentation in a single forward pass, achieving significant gains on the IGGT 3D tracking benchmark without offline mask matching or explicit 3D reconstruction.
arXiv:2609.23049v1 Announce Type: new Abstract: Large-scale scene reconstruction is a critical foundational technology in robotic autonomous systems such as 3D mapping and autonomous driving. In rece...
arXiv:2404.09431v3 Announce Type: replace Abstract: Pseudo-LiDAR has become a promising paradigm for monocular 3D object detection by transforming monocular images into point cloud representations th...
arXiv:2609.07780v2 Announce Type: replace Abstract: Automated drone surveillance has become increasingly important for public safety, critical infrastructure protection,and restricted airspace monito...
GrabVG is a visual grounding framework for UAV imagery that tackles the challenges of small, densely packed, and visually similar objects. It splits the task into preattentive hypothesis search and graph‑attentive feature binding, using distillation‑guided proposals and a sparse graph to capture intra‑ and inter‑instance relationships. Experiments on AerialVG and AerialSense show that GrabVG achieves higher accuracy and speed, outperforming baselines by significant margins.
Crane is a CLIP‑based framework for zero‑shot anomaly detection that enhances dense localization by adapting the vision encoder with a correlation‑based attention module and conditioning learnable prompts on global image context. It further fuses anomaly‑relevant patch features into the global representation for more sensitive image‑level detection, and a variant called Crane+ leverages DINOv2 spatial correlations for stronger pixel‑level performance. Across seven industrial benchmarks, Crane raises mean image‑level AP by 4.5% and Crane+ boosts mean pixel‑level AUPRO by 9.0%.
arXiv:2509. 24528v4 Announce Type: replace-cross Abstract: Object retrieval from a scene has become a new trend of research due to its numerous applications.
arXiv:2609.21424v1 Announce Type: new Abstract: Few-shot semantic segmentation (FSS) of strip steel surface defects (S$^3$D) has posed significant challenges distinct from natural scenes. Unlike natu...
arXiv:2606. 30576v1 Announce Type: cross Abstract: Cross-view object geo-localization (CVOGL) aims to locate a target object from a query view (e.