Reference-Induced Consensus for Selective Posed-Reference Visual Localization
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors present RIC-Loc, a method to determine a camera's location without needing extra scene training or detailed 3D maps. Instead, it uses known reference camera poses and predicts possible camera positions by comparing to those references. They create reliability scores to check how trustworthy each location guess is, helping to detect failures even without ground-truth data. Their approach works well indoors and outdoors, especially in scenes with varied textures, and performs comparably to other methods that rely on 3D maps.
camera localizationpose estimationStructure-from-Motion (SfM)SE(3) transformationvisual trackingcovarianceconsensus estimationpose hypothesisfailure detectionreference poses
Authors
Wonseok Kang, Jaehyun Kim, Jeongmin Lee, Tae-Wan Kim
Abstract
We present RIC-Loc (Reference-Induced Consensus localization), a scene-training-free posed-reference localizer that is SfM-point-map-free in its main estimator: it uses known reference poses, but not precomputed SfM 3D map points, query-to-map 2D-3D matches, or query-to-map PnP. A frozen VGGT pass predicts local camera poses, depth, and query-reference tracks for a query and selected references. Each reference induces one map-frame SE(3) query-pose hypothesis, robust consensus estimates the pose, and the preserved hypothesis structure yields two reliability scores: spatial dispersion and a track-conditioned covariance score. On the covariance-eligible set, the two scores are complementary for held-out, ground-truth-free failure detection across indoor, outdoor, and large-scale low-texture benchmarks: the joint policy is strongest in textured scenes and the covariance score in the low-texture regime, and the hypothesis-derived scores consistently outperform the standard retrieval-score gap and random rankings. Without per-scene training the consensus estimator remains accurate -- competitive with structure-based localization indoors and improving over a comparable feed-forward baseline -- giving an effective selective operating regime for posed-reference localization. Code is available at https://github.com/SNU-DLLAB/ric_loc.