AI Paper Atlas

Research map / 3D vision / Depth and stereo

A Neural Network for Detailed Human Depth Estimation From a Single Image

Sicong Tang, Feitong Tan, Kelvin Cheng, Zhaoyang Li, Siyu Zhu, Ping Tan

ICCV 2019 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 49 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 skeleton and segmentation cues (ablation)Depth-Net (Base + Detail) · Human depth test set (fused GT)accuracy 1.25cm: 25.74 -> 29.24Improved
add skeleton and segmentation cues (ablation)Depth-Net (Base + Detail) · Human depth test set (fused GT)MAE: 4.382 -> 3.282Improved
use two-branch base/detail separation (ablation)Depth-Net (Base + Detail) · Human depth test set (fused GT)accuracy 5.0cm: 72.97 -> 75.52Improved
use two-branch base/detail separation (ablation)Depth-Net (Base + Detail) · Human depth test set (fused GT)MAE: 3.480 -> 3.282Improved
add stage 2 joint training after stage 1 (ablation)Depth-Net (Base + Detail) · Human depth test set (fused GT)accuracy 1.25cm: 26.64 -> 29.24Improved
add stage 2 joint training after stage 1 (ablation)Depth-Net (Base + Detail) · Human depth test set (fused GT)MAE: 3.592 -> 3.282Improved
add stage 1 pre-training before stage 2 (ablation)Depth-Net (Base + Detail) · Human depth test set (fused GT)accuracy 1.25cm: 27.89 -> 29.24Improved
add stage 1 pre-training before stage 2 (ablation)Depth-Net (Base + Detail) · Human depth test set (fused GT)MAE: 3.332 -> 3.282Improved
use truncated L1 instead of Huber loss on composed shape (ablation)Depth-Net (Base + Detail) · Human depth test set (fused GT)accuracy 5.0cm: 74.23 -> 75.52Improved
use truncated L1 instead of Huber loss on composed shape (ablation)Depth-Net (Base + Detail) · Human depth test set (fused GT)MAE: 3.410 -> 3.282Improved
add iterative normal-based depth refinement (ablation)Ours · Human depth test set (fused GT)accuracy 1.25cm: 29.24 -> 30.06Improved
add iterative normal-based depth refinement (ablation)Ours · Human depth test set (fused GT)MAE: 3.282 -> 3.208Improved

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