AI Paper Atlas

Research map / 3D vision / 3D generation

Anisotropic Convolutional Networks for 3D Semantic Scene Completion

Jie Li, Kai Han, Peng Wang, Yu Liu, Xia Yuan

CVPR 2020 · 3D vision › 3D generation · approach: Semantic scene completion · 144 citations (OpenAlex)

Check 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 voxel-wise anisotropic convolution with adaptive kernel selectionAIC-Net · NYUCADSSC average IoU: 42.8 -> 45.8Improved
use voxel-wise anisotropic convolution with adaptive kernel selectionAIC-Net · NYUSSC average IoU: 32.9 -> 33.3Improved
use anisotropic convolution rather than fixed-receptive-field modelingAIC-Net · NYUscene completion IoU: 61.1 -> 59.2Hurt
use candidate kernels {3, 5, 7} instead of only kernel 7 (ablation)AIC-Net · NYUCADSSC average IoU: 44.0 -> 45.8Improved
add candidate kernel 3 to the set {5, 7} (ablation)AIC-Net · NYUCADSSC average IoU: 44.9 -> 45.8Improved
set all modulation factors to 1, removing adaptive kernel weighting (ablation)AIC-Net · NYUSSC average IoU: 33.3 -> 30.7Hurt
set all modulation factors to 1, removing adaptive kernel weighting (ablation)AIC-Net · NYUCADSSC average IoU: 45.8 -> 42.5Hurt
replace DDR blocks with AIC modules (ablation)DDRNet · NYUCADSSC-IoU: +1.6%Improved
replace ASPP with an AIC module (ablation)DDRNet · NYUCADSSC average IoU: 42.8 -> 43.4Improved
replace both DDR blocks and ASPP with AIC modules (ablation)DDRNet · NYUCADSSC average IoU: 42.8 -> 45.2Improved
use one AIC module in feature fusion instead of two (ablation)AIC-Net · NYUCADSSC-IoU: 45.8 -> 45.2Hurt

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