AI Paper Atlas

Research map / 3D vision / Depth and stereo

Rendering Portraitures from Monocular Camera and Beyond

Xiangyu Xu, Deqing Sun, Sifei Liu, Wenqi Ren, Yu-Jin Zhang, Ming-Hsuan Yang, Jian Sun

ECCV 2018 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 32 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 SPN refinement to the coarse portrait segmentationportrait segmentation · Baidu human segmentation (whole-body)IoU: 91.43 -> 93.22Improved
add SPN refinement to selfie segmentationportrait segmentation · Selfie segmentation datasetmean IoU (%): 95.52 -> 96.40Improved
refine depth with SPN trained on sparse ranking labelsdepth estimation · Depth in the Wild (DIW) testWHDR: 14.39 -> 14.35No clear effect
add the body depth-consistency loss with portrait segmentation data (ablation)SPN depth estimation · portrait depth qualitativedepth consistency on human bodyImproved
use spatially-variant RNN with depth and segmentation guidance instead of CNN (ablation)DoF approximation network · Baidu human test set (DoF approximation)PSNR (dB): 37.35 -> 40.74Improved
use spatially-variant RNN with depth and segmentation guidance instead of CNN (ablation)DoF approximation network · Baidu human test set (DoF approximation)SSIM: 0.9723 -> 0.9868Improved
add depth and segmentation guidance to RNN filtering compared with Liu et al.RNN filter · Baidu human test set (DoF approximation)PSNR (dB): 33.55 -> 40.74Improved
add depth layers to background blur (ablation)CRF-based DoF rendering · User study (22 subjects, 30 whole-body images)percent judged real SLR: 13.2% -> 79.1%Improved
add depth information to the blur (ablation)CRF-based DoF rendering · qualitative ablationvisual realismImproved
add SPN refinement of segmentation (ablation)CRF-based DoF rendering · qualitative ablationvisual realismImproved
use CRF depth layering instead of naive thresholding (ablation)CRF-based DoF rendering · qualitative ablationvisual realismImproved
add segmentation-guided blur kernel (ablation)CRF-based DoF rendering · qualitative ablationboundary artifactsImproved

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