AI Paper Atlas

Research map / Label-efficient and robust learning / Domain adaptation and generalization

S2R-DepthNet: Learning a Generalizable Depth-Specific Structural Representation

Xiaotian Chen, Yuwang Wang, Xuejin Chen, Wenjun Zeng

CVPR 2021 · Label-efficient and robust learning › Domain adaptation and generalization · approach: Geometric alignment and synthetic-to-real adaptation · 49 citations (OpenAlex)

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 STE to the raw-image depth baseline (ablation)S2R-DepthNet · vKITTI→KITTI, 0~80mAbs Rel: 0.236 -> 0.201Improved
add DSA to the STE-based model (ablation)S2R-DepthNet · vKITTI→KITTI, 0~80mAbs Rel: 0.201 -> 0.165Improved
combine the attention map with structure by element-wise multiplication instead of addition (ablation)STE + DSA depth model · vKITTI→KITTI, 0~80mAbs Rel: 0.185 -> 0.165Improved
combine the attention map with structure by element-wise multiplication instead of concatenation (ablation)STE + DSA depth model · vKITTI→KITTI, 0~80mAbs Rel: 0.179 -> 0.165Improved
use Sobel edge maps instead of the learned depth-specific representation (ablation)depth estimation baseline · vKITTI→KITTI, 0~80mAbs Rel: 0.165 -> 0.217Hurt
use semantic segmentation maps instead of the learned depth-specific representation (ablation)depth estimation baseline · vKITTI→KITTI, 0~80mAbs Rel: 0.165 -> 0.204Hurt
add STE to the raw-image baseline (ablation)S2R-DepthNet · SUNCG→NYU Depth v2Abs Rel: 0.278 -> 0.225Improved
add DSA to the STE-based model (ablation)S2R-DepthNet · SUNCG→NYU Depth v2Abs Rel: 0.225 -> 0.196Improved

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