AI Paper Atlas

Research map / 3D vision / Face and shape

Ladybird: Quasi-Monte Carlo Sampling for Deep Implicit Field Based 3D Reconstruction with Symmetry

Yifan Xu, Tianqi Fan, Yi Yuan, Gurprit Singh

ECCV 2020 · 3D vision › Face and shape · approach: Neural implicit surface reconstruction

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
sample with Grid+FPS instead of Grid+Random (ablation)Ladybird · ShapeNet testChamfer distance (x0.001): 10.17 -> 8.43Improved
sample with Grid+FPS instead of Grid+Random (ablation)Ladybird · ShapeNet testEMD (x100): 2.71 -> 2.57Improved
sample with Grid+FPS instead of Sobol+FPS (ablation)Ladybird · ShapeNet testChamfer distance (x0.001): 11.33 -> 8.43Improved
sample with Grid+FPS instead of Jitter+FPS (ablation)Ladybird · ShapeNet testChamfer distance (x0.001): 19.88 -> 8.43Improved
select subset with FPS instead of random from grid points (ablation)Grid sampler · 2D, 1024 pointsstar discrepancy (x0.01): 4.51 -> 3.86Improved
select subset with FPS instead of random (ablation)Ladybird · SDF validation accuracy, epoch 30accuracy: 0.825 -> 0.917Improved
add Symm(Concat) symmetric feature fusion (ablation)Ladybird · ShapeNet testChamfer distance (x0.001): 8.43 -> 6.33Improved
add Symm(Concat) symmetric feature fusion (ablation)Ladybird · ShapeNet testIoU (%): 61.9 -> 65.6Improved
add Symm(Near) symmetric feature fusion (ablation)Ladybird · ShapeNet testChamfer distance (x0.001): 8.43 -> 7.66Improved
fuse symmetric features by averaging (Symm(Avg)) (ablation)Ladybird · ShapeNet testChamfer distance (x0.001): 8.43 -> 19.41Hurt
use estimated instead of ground truth camera parametersLadybird · ShapeNet Core testChamfer distance (x0.001): 6.33 -> 8.60Hurt
raise Marching Cube resolution from 64^3 to 512^3 (ablation)Ladybird Grid+FPS · ShapeNet 100 objectsChamfer distance (x0.001): 9.04 -> 8.81No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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