English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper presents SIM-Sync, a certifiably optimal algorithm that estimatescamera trajectory and 3D scene structure directly from multiview imagekeypoints. SIM-Sync fills the gap between pose graph optimization and bundleadjustment; the former admits efficient global optimization but requiresrelative pose measurements and the latter directly consumes image keypoints butis difficult to optimize globally (due to camera projective geometry). Thebridge to this gap is a pretrained depth prediction network. Given a graph withnodes representing monocular images taken at unknown camera poses and edgescontaining pairwise image keypoint correspondences, SIM-Sync first uses apretrained depth prediction network to lift the 2D keypoints into 3D scaledpoint clouds, where the scaling of the per-image point cloud is unknown due tothe scale ambiguity in monocular depth prediction. SIM-Sync then seeks tosynchronize jointly the unknown camera poses and scaling factors (i.e., overthe 3D similarity group). The SIM-Sync formulation, despite nonconvex, allowsdesigning an efficient certifiably optimal solver that is almost identical tothe SE-Sync algorithm. We demonstrate the tightness, robustness, and practicalusefulness of SIM-Sync in both simulated and real experiments. In simulation,we show (i) SIM-Sync compares favorably with SE-Sync in scale-freesynchronization, and (ii) SIM-Sync can be used together with robust estimatorsto tolerate a high amount of outliers. In real experiments, we show (a)SIM-Sync achieves similar performance as Ceres on bundle adjustment datasets,and (b) SIM-Sync performs on par with ORB-SLAM3 on the TUM dataset withzero-shot depth prediction.

SIM-Sync: From Certifiably Optimal Synchronization over the 3D Similarity Group to Scene Reconstruction with Learned Depth