AI Paper Atlas

Research map / 3D vision / 3D generation

Zenseact Open Dataset: A Large-Scale and Diverse Multimodal Dataset for Autonomous Driving

Mina Alibeigi, William Ljungbergh, Adam Tonderski, Georg Hess, Adam Lilja, Carl Lindström, Daria Motorniuk, Junsheng Fu, Jenny Widahl, Christoffer Petersson

ICCV 2023 · 3D vision › 3D generation · approach: 3D perception for autonomous driving · 105 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
train detector on blurred anonymized images instead of original images (ablation)Faster R-CNN · ZOD Frames, evaluated on original imagesAP: 30.352 -> 30.117No clear effect
train detector on DNAT anonymized images instead of original images (ablation)Faster R-CNN · ZOD Frames, evaluated on original imagesAP: 30.352 -> 30.308No clear effect
use JPG compressed images instead of PNG for training (ablation)Faster R-CNN · ZOD FramesAP: 30.23 -> 30.02No clear effect
increase object distance range for 3D detectionCenterPoint · ZOD FramesmAP: 0.33 (0-50m) -> 0.01 (150-250m)Hurt
evaluate rare traffic sign classes versus common onesResNet-50 TSR baseline · ZOD traffic signsaverage accuracy: 93.4 -> 65.4Hurt

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