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 a learning-based method for multi-view depth estimationfrom posed images. Our core idea is a "learning-to-optimize" paradigm thatiteratively indexes a plane-sweeping cost volume and regresses the depth mapvia a convolutional Gated Recurrent Unit (GRU). Since the cost volume plays aparamount role in encoding the multi-view geometry, we aim to improve itsconstruction both at pixel- and frame- levels. At the pixel level, we proposeto break the symmetry of the Siamese network (which is typically used in MVS toextract image features) by introducing a transformer block to the referenceimage (but not to the source images). Such an asymmetric volume allows thenetwork to extract global features from the reference image to predict itsdepth map. Given potential inaccuracies in the poses between reference andsource images, we propose to incorporate a residual pose network to correct therelative poses. This essentially rectifies the cost volume at the frame level.We conduct extensive experiments on real-world MVS datasets and show that ourmethod achieves state-of-the-art performance in terms of both within-datasetevaluation and cross-dataset generalization.

RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo