AI Paper Atlas

Research map / Image generation / Super-resolution

Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution

Baoli Sun, Xinchen Ye, Baopu Li, Haojie Li, Zhihui Wang, Rui Xu

CVPR 2021 · Image generation › Super-resolution · approach: Perceptual and real-world SR · 48 citations (OpenAlex)

Check 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
Transfer cross-task knowledge from the auxiliary RGB depth-estimation task during training (ablation)DSRNet · Middlebury ×8MAD: 0.398 -> 0.356Improved
Transfer cross-task knowledge from the auxiliary RGB depth-estimation task during training (ablation)DSRNet · NYUv2 ×8RMSE: 3.13 -> 2.75Improved
Add output-space distillation (ablation)DSRNet with DENet · Middlebury ×8MAD: 0.398 -> 0.377Improved
Add output-space distillation (ablation)DSRNet with DENet · NYUv2 ×8RMSE: 3.13 -> 2.88Improved
Add affinity-space distillation (ablation)DSRNet with DENet · Middlebury ×8MAD: 0.398 -> 0.384Improved
Add affinity-space distillation (ablation)DSRNet with DENet · NYUv2 ×8RMSE: 3.13 -> 2.93Improved
Add both output-space and affinity-space distillation (ablation)DSRNet with DENet · Middlebury ×8MAD: 0.398 -> 0.372Improved
Add both output-space and affinity-space distillation (ablation)DSRNet with DENet · NYUv2 ×8RMSE: 3.13 -> 2.85Improved
Add structure prediction regularization (ablation)DSRNet with both distillation losses · Middlebury ×8MAD: 0.372 -> 0.356Improved
Add structure prediction regularization (ablation)DSRNet with both distillation losses · NYUv2 ×8RMSE: 2.85 -> 2.75Improved
Use uncertainty-induced attention instead of plain feature concatenation (ablation)SPNet · Middlebury Art ×8 structure predictionMAD: 1.403 -> 1.386Improved
Train the proposed single-depth method rather than DGDIEDSRNet · NYUv2 ×4RMSE: 1.56 -> 1.49Improved

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