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

Single image depth estimation is a foundational task in computer vision andgenerative modeling. However, prevailing depth estimation models grapple withaccommodating the increasing resolutions commonplace in today's consumercameras and devices. Existing high-resolution strategies show promise, but theyoften face limitations, ranging from error propagation to the loss ofhigh-frequency details. We present PatchFusion, a novel tile-based frameworkwith three key components to improve the current state of the art: (1) Apatch-wise fusion network that fuses a globally-consistent coarse predictionwith finer, inconsistent tiled predictions via high-level feature guidance, (2)A Global-to-Local (G2L) module that adds vital context to the fusion network,discarding the need for patch selection heuristics, and (3) A Consistency-AwareTraining (CAT) and Inference (CAI) approach, emphasizing patch overlapconsistency and thereby eradicating the necessity for post-processing.Experiments on UnrealStereo4K, MVS-Synth, and Middleburry 2014 demonstrate thatour framework can generate high-resolution depth maps with intricate details.PatchFusion is independent of the base model for depth estimation. Notably, ourframework built on top of SOTA ZoeDepth brings improvements for a total of17.3% and 29.4% in terms of the root mean squared error (RMSE) onUnrealStereo4K and MVS-Synth, respectively.

PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation