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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We consider the problem of simultaneously estimating a dense depth map andcamera pose for a large set of images of an indoor scene. While classical SfMpipelines rely on a two-step approach where cameras are first estimated using abundle adjustment in order to ground the ensuing multi-view stereo stage, bothour poses and dense reconstructions are a direct output of an altered bundleadjuster. To this end, we parametrize each depth map with a linear combinationof a limited number of basis "depth-planes" predicted in a monocular fashion bya deep net. Using a set of high-quality sparse keypoint matches, we optimizeover the per-frame linear combinations of depth planes and camera poses to forma geometrically consistent cloud of keypoints. Although our bundle adjustmentonly considers sparse keypoints, the inferred linear coefficients of the basisplanes immediately give us dense depth maps. RidgeSfM is able to collectivelyalign hundreds of frames, which is its main advantage over recent memory-heavydeep alternatives that can align at most 10 frames. Quantitative comparisonsreveal performance superior to a state-of-the-art large-scale SfM pipeline.

RidgeSfM: Structure from Motion via Robust Pairwise Matching Under Depth Uncertainty