AI Paper Atlas

Research map / 3D vision / 3D generation

Cascaded Context Pyramid for Full-Resolution 3D Semantic Scene Completion

Pingping Zhang, Wei Liu, Yinjie Lei, Huchuan Lu, Xiaoyun Yang

ICCV 2019 · 3D vision › 3D generation · approach: Semantic scene completion · 80 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 Cascaded Context Pyramid (CCP) instead of PPM (ablation)CCPNet · SUNCG (ablation)SC IoU: decrease 4.1% with PPM; 87.3 vs 91.4Improved
add CCP instead of ASPP (ablation)CCPNet · SUNCG (ablation)SC IoU: decrease 2.3% with ASPP; 89.1 vs 91.4Improved
use Guided Residual Block instead of basic residual blocks (ablation)CCPNet · SUNCG (ablation)SC and SSC IoU: decreasing 8.1% and 8.4% for SC and SSCImproved
add guidance to Guided Residual Block (ablation)CCPNet · SUNCG (ablation)SC/SSC IoU: 84.3 -> 91.4 SC; 67.4 -> 74.2 SSCImproved
add feature amplification to Guided Residual Block (ablation)CCPNet · SUNCG (ablation)SC/SSC IoU: 88.7 -> 91.4 SC; 73.6 -> 74.2 SSCImproved
predict at full resolution instead of quarter or half resolution (ablation)CCPNet · SUNCG (ablation)SC and SSC IoU: improving the IoUs by 4.9% and 5.1%Improved
replace 3D dilated convolutions with separated kernels (ablation)SSCNet · SUNCGSC/SSC IoU and cost: 73.5 -> 76.8 SC; 46.4 -> 52.5 SSC; params 930 -> 532Improved
use CCPNet instead of SATNet3D semantic scene completion · NYU KinectSSC average IoU: 34.4 -> 41.3Improved
add SUNCG pretraining data to NYU trainingCCPNet · NYU KinectSSC average IoU: 38.5 -> 41.3Improved
use CCPNet instead of DDRNet3D semantic scene completion · NYU Kinect efficiencyspeed and parameters: 658 ms -> 57 ms; 195k -> 89k paramsImproved

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