AI Paper Atlas

Research map / 3D vision / Face and shape

High-Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference

Xiaoguang Han, Zhen Li, Haibin Huang, Evangelos Kalogerakis, Yizhou Yu

ICCV 2017 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 333 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 AUC loss (ablation)global structure network · Chair ablation (global network)F1 of inside voxels: 0.904 -> 0.926Improved
add projected depth images (2D branch) (ablation)global structure network · Chair ablation (global network)F1 of inside voxels: 0.877 -> 0.926Improved
add BLSTM context modeling (ablation)global structure network · Chair ablation (global network)F1 of inside voxels: 0.896 -> 0.926Improved
add BSurf channel to CSDF input (ablation)global structure network · Chair ablation (global network)F1 of inside voxels: 0.90 -> 0.926Improved
add CSDF channel to BSurf-only input (ablation)global structure network · Chair ablation (global network)F1 of inside voxels: 0.836 -> 0.926Improved
use 1x1x1 conv head instead of encoder-decoder (ablation)global structure network · Chair ablation (global network)F1 of inside voxels: 0.818 -> 0.926Improved
add global guidance from global network (ablation)local refinement network · Chair ablation (local network)accuracy: 0.912 -> 0.961Improved
local refinement at 256^3 instead of 32^3 global network alonewhole network · Chair completioncompleteness: 70.1% -> 97.25%Improved
local refinement at 256^3 instead of 32^3 global network alonewhole network · Chair completionnormalized distance: 0.0108 -> 0.00398Improved
patch-based learned completion instead of Poisson reconstructionwhole network · Guitar completionnormalized distance: 0.148 -> 0.00248Improved
learned completion instead of Poisson reconstructionwhole network · Car completioncompleteness: 82.18% -> 95.88%Improved
larger missing regions (one side missing, 55.68% input completeness)whole network · Chair, large missing regionsF1 of global network: 0.926 -> 0.895Mixed

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