AI Paper Atlas

Research map / 3D vision / 3D generation

DeepContext: Context-Encoding Neural Pathways for 3D Holistic Scene Understanding

Yinda Zhang, Mingru Bai, Pushmeet Kohli, Shahram Izadi, Jianxiong Xiao

ICCV 2017 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 69 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
combine context network with DSS local detectorDSS · SUN RGB-D 3D detectionmAP (%): 43.76 -> 50.50Improved
add ground-truth alignment instead of estimated transformation (ablation)DeepContext · SUN RGB-D 3D detectionmAP: +2.19%Improved
add ground-truth template category on top of GT alignment (ablation)DeepContext · SUN RGB-D 3D detectionmAP: +1.52%Improved
combine context model with DSS on imperfect-template imagesDSS · SUN RGB-D (extended set)mAP (%): 26.80 -> 29.00Improved
use 3D context network instead of COG for scene understanding precisionDeepContext · SUN RGB-D scene understandinggeometry precision (%): 66.93 -> 71.02Improved
use transformation network instead of ICP for rotation (sleeping area, with symmetry)transformation network · SUN RGB-D alignmentrotation accuracy: 96.3% -> 100.0%Improved
use transformation network instead of ICP for rotation (lounging area, no symmetry)transformation network · SUN RGB-D alignmentrotation accuracy: 58.5% -> 71.7%Improved
use transformation network instead of ICP for translation (sleeping area)transformation network · SUN RGB-D alignmenttranslation error (m): 0.473 -> 0.278Improved
add 3D context network on top of initial floor alignment (sleeping area)DeepContext · SUN RGB-D layoutfloor error mean/median (m): 0.30/0.25 -> 0.10/0.09Improved
add 3D context network on top of initial wall (office area)DeepContext · SUN RGB-D layoutwall error mean/median (m): 0.70/0.60 -> 0.60/0.21Improved
use DeepContext alone instead of DSSDeepContext · SUN RGB-D 3D detectionspeed (s per image): 20 -> 0.5Improved
use DeepContext alone instead of DSS for chairsDeepContext · SUN RGB-D 3D detection (chair)AP: 79.1 -> 44.5Hurt

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