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

Monocular depth estimation is a challenging task that predicts the pixel-wisedepth from a single 2D image. Current methods typically model this problem as aregression or classification task. We propose DiffusionDepth, a new approachthat reformulates monocular depth estimation as a denoising diffusion process.It learns an iterative denoising process to `denoise' random depth distributioninto a depth map with the guidance of monocular visual conditions. The processis performed in the latent space encoded by a dedicated depth encoder anddecoder. Instead of diffusing ground truth (GT) depth, the model learns toreverse the process of diffusing the refined depth of itself into random depthdistribution. This self-diffusion formulation overcomes the difficulty ofapplying generative models to sparse GT depth scenarios. The proposed approachbenefits this task by refining depth estimation step by step, which is superiorfor generating accurate and highly detailed depth maps. Experimental results onKITTI and NYU-Depth-V2 datasets suggest that a simple yet efficient diffusionapproach could reach state-of-the-art performance in both indoor and outdoorscenarios with acceptable inference time.

DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation