AI Paper Atlas

Research map / 3D vision / Face and shape

Learning 3D Shapes as Multi-Layered Height-maps using 2D Convolutional Networks

Kripasindhu Sarkar, Basavaraj Hampiholi, Kiran Varanasi, Didier Stricker

ECCV 2018 · 3D vision › Face and shape · approach: Primitive-based shape abstraction · 31 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
replace element-wise max merge with concatenation followed by convolution (independent branches) (ablation)3-view MLH VGG16 · ModelNet40accuracy (%): 91.29 -> 93.11Improved
use independent (non-shared) view branches with max merge (ablation)3-view MLH VGG16 · ModelNet40accuracy (%): 91.25 -> 91.29No clear effect
initialize from ImageNet-pretrained VGG16 instead of random weights (ablation)3-view MLH VGG16 · ModelNet40accuracy (%): 89.63 -> 93.11Improved
copy pretrained RGB weights into 5-channel first layer instead of random first layer (ablation)MLH VGG16 · ModelNet10/ModelNet40test accuracy: approximately 0.1%Improved
increase number of MLH layers from 1 to 2 and up to 5 (ablation)3-view MLH merged model · ModelNet40accuracy: higher than 90.5% with 1 layer; big jump from layer 1 to 2, slow saturation till layer 5Improved
use concatenation+convolution merge with 1-layer descriptors instead of shared max (MVCNN style) (ablation)1-layer MLH, 3 views · ModelNet40accuracy (%): 89.78 -> 90.72Improved
use independent branches with max merge instead of shared with max for 1-layer descriptors (ablation)1-layer MLH, 3 views · ModelNet40accuracy (%): 89.78 -> 90.15Improved
replace VGG16 with ResNet50 or Inception models (ablation)MLH classifier · ModelNet40test accuracyNo clear effect
use 3 MLH views with cat merge instead of 80-view MVCNN rendered imagesshape classification · ModelNet40accuracy (%): 90.10 -> 93.11Improved
use single-view MLH 2D CNN instead of OctNet 256 voxel networkshape classification · ModelNet10accuracy (%): 90.3 -> 90.97Improved

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