AI Paper Atlas

Research map / 3D vision / 3D generation

Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception

Xiaqing Pan, Nicholas Charron, Yongqian Yang, Scott Peters, Thomas Whelan, Chen Kong, Omkar Parkhi, Richard Newcombe, Yuheng (Carl) Ren

ICCV 2023 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 100 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
evaluate in office scene instead of apartment (lower ceilings for mocap cameras)ADT ground-truth pipeline · ADT system accuracyobject translation error (mm): 6.94 -> 4.48Improved
evaluate in office scene instead of apartmentADT ground-truth pipeline · ADT system accuracymeasured reprojection error (pixel): 6.9 -> 4.18Improved
optimize object pose against hand-labelled markersADT measured poses · ADT system accuracyreprojection error (pixel): 6.78 -> 0.56Improved
use FPN instead of ViT-Det backboneCOCO-pretrained detectors on ADT · ADT 2D detectionAP-box (%): 11.42 -> 21.36Improved
use FPN instead of ViT-Det backboneCOCO-pretrained detectors on ADT · ADT 2D segmentationAP-mask (%): 11.64 -> 19.81Improved
use Cube R-CNN instead of Total3D3D detectors on ADT · ADT 3D detection, chairAP (%): 0.847 -> 3.72Improved
use Cube R-CNN instead of Total3D3D detectors on ADT · ADT 3D detection, fridgeAP (%): 0.048 -> 2.601Improved
use Cube R-CNN instead of Total3D3D detectors on ADT · ADT 3D detection, sofaAP (%): 1.298 -> 1.252Hurt
apply LDM image translation to synthetic ADT imagesSynthetic ADT renderings · ADT synthetic-to-real translationPSNR: 16.383 -> 24.218Improved
apply LDM image translation to synthetic ADT imagesSynthetic ADT renderings · ADT synthetic-to-real translationLPIPS: 0.270 -> 0.126Improved
use Pix2Pix instead of LDMImage translation on ADT · ADT synthetic-to-real translationSSIM: 0.660 -> 0.674Improved
use TSIT instead of LDMImage translation on ADT · ADT synthetic-to-real translationPSNR: 24.218 -> 21.885Hurt

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