AI Paper Atlas

Research map / 3D vision / Depth and stereo

PLADE-Net: Towards Pixel-Level Accuracy for Self-Supervised Single-View Depth Estimation With Neural Positional Encoding and Distilled Matting Loss

Juan Luis Gonzalez, Munchurl Kim

CVPR 2021 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 23 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
add neural positional encoding (ablation)PLADE-Net, stage 1 · KITTI improved Eigen test split, K+CSδ¹: 0.938 -> 0.942Improved
add direct pixel-coordinate positional encoding instead of no positional encoding (ablation)PLADE-Net, stage 1 · KITTI improved Eigen test split, K+CSδ¹: 0.938 -> 0.939No clear effect
add neural positional encoding (ablation)PLADE-Net, stage 2 · KITTI improved Eigen test split, K+CSδ¹: 0.942 -> 0.949Improved
add direct pixel-coordinate positional encoding instead of no positional encoding (ablation)PLADE-Net, stage 2 · KITTI improved Eigen test split, K+CSδ¹: 0.942 -> 0.945Improved
add neural positional encoding rather than direct coordinate encoding (ablation)PLADE-Net, stage 2 · KITTI improved Eigen test split, K+CSδ¹: 0.945 -> 0.949Improved
add distilled matting Laplacian loss (ablation)PLADE-Net with no proposed losses · KITTI improved Eigen test split, stage 2, K+CSδ¹: 0.943 -> 0.948Improved
add deep corr-L1 loss (ablation)PLADE-Net with no proposed losses · KITTI improved Eigen test split, stage 2, K+CSδ¹: 0.943 -> 0.945Improved
add distilled matting Laplacian loss rather than deep corr-L1 loss (ablation)PLADE-Net · KITTI improved Eigen test split, stage 2, K+CSδ¹: 0.945 -> 0.948Improved
add deep corr-L1 loss alongside the distilled matting loss (ablation)PLADE-Net with matting loss · KITTI improved Eigen test split, stage 2, K+CSδ¹: 0.948 -> 0.948No clear effect
use K+CS training rather than K-only training (ablation)PLADE-Net with NPE, stage 2 · KITTI improved Eigen test splitδ¹: 0.944 -> 0.949Improved

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