AI Paper Atlas

Research map / 3D vision / Depth and stereo

CLIFFNet for Monocular Depth Estimation with Hierarchical Embedding Loss

Lijun Wang, Jianming Zhang, Yifan Wang, Huchuan Lu, Xiang Ruan

ECCV 2020 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 67 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
add HEG-S hierarchical embedding loss to L1 loss (ablation)CLIFFNet · NYU-Depth V2 (CLIFFNet)RMSE: 0.529 -> 0.493Improved
add HEG-R hierarchical embedding loss to L1 loss (ablation)CLIFFNet · NYU-Depth V2 (CLIFFNet)RMSE: 0.529 -> 0.497Improved
add HEG-S hierarchical embedding loss to L1 loss (ablation)CLIFFNet · NYU-Depth V2 (CLIFFNet)P1: 0.817 -> 0.844Improved
use HEG-S loss instead of depth gradient loss (ablation)CLIFFNet · NYU-Depth V2 (CLIFFNet)RMSE: 0.513 -> 0.493Improved
use HEG-S loss instead of depth aware loss (ablation)CLIFFNet · NYU-Depth V2 (CLIFFNet)RMSE: 0.511 -> 0.493Improved
train HEG on relevant task rather than randomly initialize it (ablation)HEG-R loss · NYU-Depth V2 (CLIFFNet)RMSE: 0.517 -> 0.497Improved
train HEG on depth-relevant task rather than ImageNet classification (ablation)hierarchical loss · NYU-Depth V2 (CLIFFNet)RMSE: 0.523 -> 0.493Improved
add scene classification as multi-task head instead of HEG-S loss (ablation)CLIFFNet with L1 · NYU-Depth V2 (CLIFFNet)RMSE: 0.529 -> 0.530No clear effect
use scale invariant loss in addition to L1 (ablation)CLIFFNet · NYU-Depth V2 (CLIFFNet)RMSE: 0.529 -> 0.520Improved
add attention-based low-level feature refinement to CLIFF module (ablation)CLIFFNet with HEG-S · NYU-Depth V2 (CLIFFNet)RMSE, Abs Rel, P1, P2Improved
add multi-level feature selection to CLIFF module (ablation)CLIFFNet with HEG-S · NYU-Depth V2 (CLIFFNet)RMSE, Abs Rel, P1, P2Improved
add identity mapping of high-level features to CLIFF module (ablation)CLIFFNet with HEG-S · NYU-Depth V2 (CLIFFNet)RMSE, Abs Rel, P1, P2Improved

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