Classical image correspondence is solved at the level of sparse keypoints or dense pixels, but the systems that consume these matches - object-level mapping, topological navigation, scene-graph maintenance - reason about whole objects. Recent work narrows this gap by matchng directly at the level of instance segments: a class-agnostic segmenter partitions each image, and per-segment descriptors are obtained by pooling features from large 3D foundation models over the masks.
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...
By Xin Li, Siyuan Duan, Shang Wang, Zhimin Mao, Bingliang Hu, Geng Zhang
HiSfM introduces a hierarchical coarse‑to‑fine Structure‑from‑Motion framework that enhances robustness and efficiency by building a scaffold of local communities and a compact skeleton using edge‑disjoint spanning trees. The method verifies skeletal edges with a two‑view disambiguator, constructs a stable scaffold as an anchor, and then registers remaining images for refinement. Experiments on ambiguity‑focused benchmarks and general datasets demonstrate that HiSfM avoids ambiguity‑induced failures, reduces runtime, and improves completeness compared to prior approaches.
By Ziding Zhao, Hainan Cui, Peilin Tao, Shuhan Shen
DXPR is a depth‑based cross‑modal place recognition framework that matches monocular camera queries to a LiDAR map using a single vision foundation model backbone. By converting both modalities into a unified depth image representation, DXPR learns modality‑invariant global descriptors without modality‑specific encoders. A geometry‑aware overlap miner refines pairwise metric learning by computing pixel‑level overlap scores, and extensive tests on KITTI and Boreas show strong performance across seasons, weather, and day/night conditions, outperforming prior CMPR baselines.
arXiv:2512. 16919v2 Announce Type: replace-cross Abstract: Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving.
By Sicheng Zuo, Zixun Xie, Wenzhao Zheng, Shaoqing Xu, Fang Li, Shengyin Jiang, Long Chen, Zhi-Xin Yang, Jiwen Lu
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.
3D vision-language models (3D VLMs) enable spatial reasoning over multi-view scenes but suffer from substantial token redundancy due to duplicated observations and large uninformative regions, leading to high computational cost. Although visual token compression has shown promise in accelerating 2D VLMs, it fails to capture the structured nature of 3D scenes and leads to incomplete spatial coverage and loss of fine-grained details.
arXiv:2606. 19733v1 Announce Type: cross Abstract: Efficiently retrieving specific 3D instances from large-scale scenes via natural language prompts remains a formidable challenge in multimedia analysis.
By Xiuyuan Zhu, Ke Lu, Zijie Yang, Chao Yue, Jian Xue, Dongming Zhang
The paper introduces Self-Geometry, a plug‑and‑play test‑time adaptation framework that enforces explicit multi‑view geometric constraints on Vision Foundation Models (VFMs) using 2D pixel correspondences as pseudo ground truth. It combines Geometric Disentanglement Optimization—mixing Multi‑View and Epipolar Consistency losses with Gradient Disentanglement—to avoid gradient conflicts, a Frame Angular‑Neighbor sampler based on SO(3) geodesic distances to select informative views, and a Lightweight TTA module that adapts VFMs via LoRA. Experiments on six VFMs and four benchmarks (7Scenes, ETH3D, ScanNet++, HiRoom) show consistent improvements in pose and geometry estimation.
By Seokhyun Youn, Dahyeon Kye, Sung-Ho Bae, Jihyong Oh
arXiv:2602. 08058v3 Announce Type: replace-cross Abstract: In the presence of occlusions and measurement noise, geometrically accurate scene reconstructions -- which fit the sensor data -- can still be physically incorrect.
By Xihang Yu, Rajat Talak, Lorenzo Shaikewitz, Luca Carlone
arXiv:2609.08345v1 Announce Type: cross
Abstract: Representing a 3D scene as multi-view images allows 2D VLMs to reason in 3D by reusing priors from pre-training, sidestepping the scarcity of annotat...
By Nhat-Tan Bui, Varshini Elangovan, Arun Reddy Anugu, Sreyas Mohan, Wei Ye, Dilin Wang, JQ Huang, Rakesh Ranjan, Aviral Chharia, Fernando De la Torre
GeoMAD is a multi‑view anomaly detection framework that fuses multiple camera viewpoints while maintaining geometric awareness and scalability to multi‑class industrial settings. It introduces a Cross‑view Deformable Fusion Module (CDFM) that learns view‑pair‑specific sampling offsets on 2D feature maps, enabling hierarchical cross‑view correspondence without camera calibration or voxel construction. Additionally, Distributional View Alignment (DVA) provides a self‑supervised loss that aligns bottleneck distributions across views, ensuring global consistency without pixel‑level correspondence. Together, CDFM and DVA achieve geometry‑aware, distribution‑consistent fusion and demonstrate strong detection and localization performance on Real‑IAD and MANTA‑Tiny datasets.
By Shang-Fu Chen, Jhih-Ciang Wu, Kuan-Chuan Peng, Wen-Huang Cheng, Kai-Lung Hua