arXiv Computer Vision
Geometry-Aware Epipolar Correspondence Graphs for Monocular Visual Odometry
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 21
SFVO: Decoupled Confidence-Guided Stereo-Flow Visual Odometry with Bidirectional PnP
SFVO is a stereo visual‑odometry framework that leverages pretrained stereo‑matching and optical‑flow models to obtain dense stereo and temporal correspondences. Rather than learning pose directly from images, it maps these correspondences into geometric constraints and predicts trustworthy points using decoupled confidence maps for rotation and translation. Experiments on both outdoor and indoor datasets show that SFVO delivers robust, accurate pose estimation with strong generalization, and the authors plan to release the code.
arXiv Computer Vision
Sep 18
Monocular Visual Odometry without Calibration or Test-time Optimization
The paper introduces CalfVO, a monocular visual odometry system that operates without camera intrinsics, test‑time optimization, bundle adjustment, or loop closure. Using a transformer, it predicts relative poses with separate rotation and translation confidences over overlapping image windows, then aggregates these predictions via a confidence‑weighted module to produce a single trajectory. CalfVO achieves the highest accuracy among calibration‑free methods across five benchmarks and runs at 53 FPS, outperforming all baselines.
arXiv Computer Vision
Oct 27
Learning Scene Coordinate Reconstruction from Unposed Images via Pose Graph Optimization
arXiv:2610.35501v1 Announce Type: new Abstract: Learning-based structure-from-motion methods such as ACE-Zero have demonstrated strong performance in estimating cameraposes and scene coordinates from...
arXiv Computer Vision
Oct 15
PROSE: Training-Free Egocentric Scene Registration with Vision-Language Models
arXiv:2606.16569v2 Announce Type: replace Abstract: Registering two captures of the same indoor space taken at different times underpins persistent spatial memory for robots and AR systems, yet the r...
arXiv Computer Vision
Sep 14
Spectral Consistency-Guided Multiview Point Cloud Registration for Low-Overlap Scenes
The paper introduces GMPCR, a non‑learning spectral consistency‑guided framework for multiview point cloud registration in low‑overlap scenes. GMPCR refines initial correspondences into a second‑order compatibility structure, uses spectral analysis to filter unreliable matches and select informative scan pairs, and then applies maximal‑clique hypothesis generation for robust relative transformations. The resulting sparse pose graph is further refined with an adaptive history‑aware synchronization scheme, and a recovery mechanism allows previously down‑weighted edges to regain confidence, achieving high registration recalls on benchmark datasets while reducing computational cost.
arXiv Computer Vision
Sep 10
Learning Global Camera Poses from Noisy View-Graphs for Structure from Motion
arXiv:2609.09491v1 Announce Type: new Abstract: Camera pose estimation is a key step in 3D reconstruction and view-synthesis pipelines. We present a deep, global Structure-from-Motion framework based...