AI Paper Atlas

Research map / 3D vision / Face and shape

Learning Shape Templates With Structured Implicit Functions

Kyle Genova, Forrester Cole, Daniel Vlasic, Aaron Sarna, William T. Freeman, Thomas Funkhouser

ICCV 2019 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 342 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
use structured implicit template instead of voxel grid (3D-R2N2)3D-R2N2 · ShapeNet single-view reconstruction (mean, threshold tau)F-score (%): 39 -> 48Improved
use structured implicit template instead of voxel grid (3D-R2N2)3D-R2N2 · ShapeNet single-view reconstruction (mean, threshold 2 tau)F-score (%): 55 -> 70Improved
use structured implicit template instead of point set (PSG)PSG · ShapeNet single-view reconstruction (mean, threshold tau)F-score (%): 49 -> 48No clear effect
use structured implicit template instead of point set (PSG)PSG · ShapeNet single-view reconstruction (mean, threshold 2 tau)F-score (%): 70 -> 70No clear effect
use structured implicit template instead of Pix2Mesh meshPix2Mesh · ShapeNet single-view reconstruction (mean, threshold tau)F-score (%): 60 -> 48Hurt
use structured implicit template instead of Pix2Mesh meshPix2Mesh · ShapeNet single-view reconstruction (mean, threshold 2 tau)F-score (%): 74 -> 70Hurt
use structured implicit template instead of Pix2Mesh meshPix2Mesh · ShapeNet bench (threshold 2 tau)F-score (%): 72 -> 82Improved
use structured implicit template instead of Pix2Mesh meshPix2Mesh · ShapeNet table (threshold tau)F-score (%): 66 -> 40Hurt
decode with an LSTM predicting each shape element in succession instead of one fully connected layer (ablation)feed-forward CNN template network · ShapeNet 3D-to-template fittingfit qualityMixed
replace the 5-layer CNN encoder with ResNet (ablation)depth-image template network · ShapeNet 3D-to-template fittingconvergence and generalizationHurt
use ResNet V2 50 with ImageNet pretraining instead of the depth-image CNN for RGB input (ablation)RGB-to-template network · ShapeNet RGB to templatefit qualityImproved

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