arXiv Computer Vision
Queryable Gaussian View Index: Text Retrieval and Selective Camera Localization
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Sep 17
RIM: A Retrieval-In-Matching Framework for Cross-Domain Global Visual Localization of UAVs
arXiv:2607.20116v2 Announce Type: replace Abstract: Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention. However, diff...
Hugging Face Trending Papers
Jul 22
RIM: A Retrieval-In-Matching Framework for Cross-Domain Global Visual Localization of UAVs
Global visual localization of unmanned aerial vehicles (UAVs) using remote-sensing reference maps has attracted increasing attention. However, acquisition-time and imaging-platform differences between UAV and reference imagery induce substantial cross-domain appearance and viewpoint shifts, challenging robust six-degree-of-freedom (6-DoF) pose estimation.
arXiv Computer Vision
Sep 3
GeoStore: Finding Small Storefronts in Large Scenes -- A Fine-Grained POI Localization Benchmark with Global-to-Local Asymmetric Matching
GeoStore is a new benchmark for fine‑grained point‑of‑interest (POI) localization that matches close‑up storefront photos against large geo‑tagged street‑view images, a task distinct from traditional visual place recognition. The paper shows that global‑descriptor methods designed for symmetric matching perform poorly on this asymmetric problem, and introduces GLAM, a Global‑to‑Local Asymmetric Matching approach that combines a global retrieval anchor with a lightweight local re‑ranking using pooled region tokens. GLAM achieves higher Recall@1/5/10 and mAP than strong baselines while using far fewer re‑ranking features and significantly lower per‑pair matching cost.
arXiv Computer Vision
6d ago
SplatScout: Query-Driven Part-Level Referring Segmentation in Gaussian Scenes
SplatScout is a new query‑driven, closed‑loop approach for part‑level referring segmentation in Gaussian scenes, placing perception under vision‑language model control. It actively selects views, directs segmentation, and refines predictions by inspecting rendered 3D results. On the newly introduced PartRef‑ScanNet++ benchmark, SplatScout achieves 0.538 mIoU, outperforming existing methods and demonstrating the benefits of iterative refinement and effective tool‑feedback utilization.
arXiv Computer Vision
Oct 23
SpatialMem: Metric-Aligned Long-Horizon Video Memory for Language Grounding and QA
SpatialMem is a memory-based system that fuses 3D geometry, semantics, and language into a single queryable representation. Starting from casually recorded egocentric RGB video, it reconstructs metrically scaled interior scenes, identifies structural 3D anchors (walls, doors, windows), and links open‑vocabulary object nodes to evidence patches, visual embeddings, and two‑layer descriptions at 3D coordinates, enabling spatial‑relation reasoning, language‑directed retrieval, and QA without special sensors. The system is evaluated at scale on public benchmarks, achieving competitive scores on VSI‑Bench, OpenEQA, and ScanNet, while maintaining a compact index of about 14 KB per scene.
arXiv Computer Vision
Sep 1
CapFrame: Text-Instructed Viewpoint Grounding in 3D Gaussian Scenes via Geometric Pseudo Labels
arXiv:2608.30342v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables photorealistic real-time novel view synthesis, yet placing a virtual camera to capture a desired frame remains lar...