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

Multi-View Stereo~(MVS) is a fundamental problem in geometric computer visionwhich aims to reconstruct a scene using multi-view images with known cameraparameters. However, the mainstream approaches represent the scene with a fixedall-pixel depth range and equal depth interval partition, which will result ininadequate utilization of depth planes and imprecise depth estimation. In thispaper, we present a novel multi-stage coarse-to-fine framework to achieveadaptive all-pixel depth range and depth interval. We predict a coarse depthmap in the first stage, then an Adaptive Depth Range Prediction module isproposed in the second stage to zoom in the scene by leveraging the referenceimage and the obtained depth map in the first stage and predict a more accurateall-pixel depth range for the following stages. In the third and fourth stages,we propose an Adaptive Depth Interval Adjustment module to achieve adaptivevariable interval partition for pixel-wise depth range. The depth intervaldistribution in this module is normalized by Z-score, which can allocate densedepth hypothesis planes around the potential ground truth depth value and viceversa to achieve more accurate depth estimation. Extensive experiments on fourwidely used benchmark datasets~(DTU, TnT, BlendedMVS, ETH 3D) demonstrate thatour model achieves state-of-the-art performance and yields competitivegeneralization ability. Particularly, our method achieves the highest Acc andOverall on the DTU dataset, while attaining the highest Recall and$F_{1}$-score on the Tanks and Temples intermediate and advanced dataset.Moreover, our method also achieves the lowest $e_{1}$ and $e_{3}$ on theBlendedMVS dataset and the highest Acc and $F_{1}$-score on the ETH 3D dataset,surpassing all listed methods.Project website:https://github.com/zs670980918/ARAI-MVSNet

ARAI-MVSNet: A multi-view stereo depth estimation network with adaptive depth range and depth interval