AI Paper Atlas

Research map / Image generation / Super-resolution

Perceptual Deep Depth Super-Resolution

Oleg Voynov, Alexey Artemov, Vage Egiazarian, Alexander Notchenko, Gleb Bobrovskikh, Evgeny Burnaev, Denis Zorin

ICCV 2019 · Image generation › Super-resolution · approach: Efficient lightweight super-resolution · 48 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace depth-difference loss with visual difference loss (MSG to MSG-V)MSG · SimGeo average x4RMSEv (x1e-3): 194 -> 99Improved
replace depth-difference loss with visual difference loss (MSG to MSG-V)MSG · SimGeo average x4DSSIMv (x1e-3): 374 -> 95Improved
replace depth-difference loss with visual difference loss (MSG to MSG-V)MSG · SimGeo average x4LPIPSv (x1e-3): 569 -> 194Improved
replace depth-difference loss with visual difference loss (MSG to MSG-V)MSG · SimGeo average x4RMSEd (mm): 39 -> 96Hurt
replace depth-difference loss with visual difference loss (DIP to DIP-V)DIP · SimGeo average x4DSSIMv (x1e-3): 887 -> 313Improved
replace depth-difference loss with visual difference loss (DIP to DIP-V)DIP · SimGeo average x4RMSEv (x1e-3): 395 -> 147Improved
replace depth-difference loss with visual difference loss (DIP to DIP-V)DIP · SimGeo average x4RMSEd (mm): 52 -> 33Improved
use RMSEv rather than DSSIM as the training loss (ablation)depth super-resolution optimization · single example (Figure 3)DSSIM: 0.396 -> 0.254Improved
evaluate with RMSEd versus perceptual metrics (correlation)quality measures · super-resolution results (Figure 4)Pearson correlation with LPIPS: 0.85Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy