AI Paper Atlas

Research map / 3D vision / 3D generation

NDC-Scene: Boost Monocular 3D Semantic Scene Completion in Normalized Device Coordinates Space

Jiawei Yao, Chuming Li, Keqiang Sun, Yingjie Cai, Hao Li, Wanli Ouyang, Hongsheng Li

ICCV 2023 · 3D vision › 3D generation · approach: Semantic scene completion · 140 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
extend 2D features to NDC space with dual decoder instead of FLoSP lifting with heavy 3D UNet (ablation)NDC-Scene · NYUv2mIoU: 27.69 -> 29.03Improved
extend 2D features to NDC space with dual decoder instead of FLoSP lifting (ablation)NDC-Scene · SemanticKITTI valIoU: 37.15 -> 37.24No clear effect
put 3D computation in NDC space instead of camera space (ablation)NDC-Scene · NYUv2mIoU: 28.10 -> 29.03Improved
put 3D computation in NDC space instead of camera space (ablation)NDC-Scene · SemanticKITTI valIoU: 37.20 -> 37.24No clear effect
use depth adaptive attention instead of naive feature addition (ablation)NDC-Scene · NYUv2mIoU: 28.22 -> 29.03Improved
use depth adaptive attention instead of naive feature addition (ablation)NDC-Scene · SemanticKITTI valmIoU: 11.22 -> 12.70Improved
use NDC-Scene instead of MonoScene on NYUv2monocular SSC · NYUv2 testmIoU: 26.94 -> 29.03Improved
use NDC-Scene instead of MonoScene on SemanticKITTImonocular SSC · SemanticKITTI valmIoU: 11.50 -> 12.70Improved
randomly rotate target space by up to 15 degrees (pose ambiguity test) (ablation)NDC-Scene vs MonoScene · NYUv2 testmIoU: NDC-Scene 29.03 -> 22.39; MonoScene 26.94 -> 16.71Hurt

Later papers that compared with this method

5 later accepted papers report NDC-Scene as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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