AI Paper Atlas

Research map / 3D vision / 3D generation

3D-RelNet: Joint Object and Relational Network for 3D Prediction

Nilesh Kulkarni, Ishan Misra, Shubham Tulsiani, Abhinav Gupta

ICCV 2019 · 3D vision › 3D generation · approach: Open-vocabulary 3D scene understanding · 48 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 unary and relative predictions at both train and test time (ablation)multi-task model · SUNCG (ground-truth boxes, combination ablation)translation accuracy %: 81.9 -> 84.0Improved
combine predictions at test time only (ablation)multi-task model · SUNCG (ground-truth boxes, combination ablation)translation accuracy %: 81.9 -> 83.5Improved
combine predictions at train time only (ablation)multi-task model · SUNCG (ground-truth boxes, combination ablation)translation accuracy %: 81.9 -> 82.0No clear effect
add object location mask to relative network input (ablation)3D-RelNet · SUNCG (ground-truth boxes, feature ablation)scale accuracy %: 56.1 -> 69.7Improved
add object location mask to relative network input (ablation)3D-RelNet · SUNCG (ground-truth boxes, feature ablation)translation accuracy %: 82.7 -> 84.0Improved
add spatial coordinates to input (ablation)3D-RelNet · SUNCG (ground-truth boxes, feature ablation)rotation accuracy (err <= 30 deg %): 82.4 -> 86.6Improved
add spatial coordinates to input (ablation)3D-RelNet · SUNCG (ground-truth boxes, feature ablation)scale accuracy %: 70.4 -> 69.7Hurt
replace per-object prediction with pairwise relationship reasoningFactored3D · SUNCG (ground-truth boxes)translation mean error (m): 0.39 -> 0.33Improved
add CRF relationship modelFactored3D · SUNCG (ground-truth boxes)translation accuracy %: 79.5 -> 79.7No clear effect
use 3D-RelNet instead of GCNGCN · SUNCG (ground-truth boxes)scale accuracy %: 69.1 -> 69.7No clear effect
use 3D-RelNet with detector boxesFactored3D · SUNCG (detection setting)mAP (all criteria): 21.72 -> 27.76Improved
use 3D-RelNet with detector boxesFactored3D · NYUv2 (detection setting)mAP (all criteria): 5.30 -> 8.49Improved

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