MVLoMa is a sparse star‑graph matcher that extends the LoMa local‑feature matching framework from image pairs to multi‑view settings. It uses a frozen multi‑view geometry model to jointly describe all images in a star, injecting cross‑view geometric context into local descriptors and performing centre‑to‑neighbour matching in a single forward pass with per‑view self‑attention and bidirectional centre‑neighbour cross‑attention. On 25‑view star graphs from HyperSim, ScanNet++, Mip‑NeRF 360, and Tanks and Temples, MVLoMa achieves the best macro‑average relative‑pose AUC at all thresholds and is 2.20 times faster than sequential pairwise evaluation, while supporting multiple frozen geometry encoders and demonstrating the benefits of geometry‑aware descriptors, visibility filtering, geometric negative supervision, and joint multi‑view inference.
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:2606.29167v2 Announce Type: replace
Abstract: Dense correspondence on in-the-wild 3D scans must handle severe non-isometric deformation, partial observations, topology artifacts, irregular disc...
By Qilong Liu, Qinfeng Xiao, Chenyuan Yi, Yongsheng Lin, Liying Zhang, Kit-lun Yick
arXiv:2606.03406v2 Announce Type: replace
Abstract: Reliable correspondence estimation supports image processing and 3D vision tasks, including Structure from Motion, visual localization, and image r...
By Xu Pan, Zhen Pang, Qiyuan Ma, Wei Ji, Shuhan Shen, Xianwei Zheng
arXiv:2607.02486v2 Announce Type: replace
Abstract: Descriptor-free visual localization eliminates high-dimensional descriptor storage, preserves scene privacy, and simplifies map maintenance, yet it...
By Yejun Zhang, Xinjue Wang, Zihan Wang, Esa Rahtu, Juho Kannala
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