AI Paper Atlas

Research map / Point clouds / Segmentation and detection

Toward Generating Realistic 3D Semantic Training Data for Autonomous Driving

Lucas Nunes, Rodrigo Marcuzzi, Jens Behley, Cyrill Stachniss

TPAMI 2026 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation · 7 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
use single sparse 3D latent diffusion instead of XCube multi-resolution at 0.1 m3D scene generator · SemanticKITTI generated scenes (0.1 m)MMD: 0.101 -> 0.073Improved
use single sparse 3D latent diffusion instead of XCube at 0.2 m3D scene generator · SemanticKITTI generated scenes (0.2 m)MMD: 0.160 -> 0.146Improved
use single-VAE method instead of XCube for realism measured by real-trained segmenter at 0.1 m3D scene generator · mIoU on generated scenes (0.1 m)mIoU: 27.24 -> 53.09Improved
use single-VAE method instead of XCube at 0.2 m3D scene generator · mIoU on generated scenes (0.2 m)mIoU: 40.02 -> 50.83Improved
increase resolution from 0.2 m to 0.1 mOurs · mIoU on generated scenesmIoU: 50.83 -> 53.09Improved
increase resolution from 0.2 m to 0.1 mXCube · mIoU on generated scenesmIoU: 40.02 -> 27.24Hurt
complement 10% real data with our synthetic scenes (LiDAR-simulated)segmentation network · SemanticKITTI val, LiDAR-simulatedmIoU: 45.58 -> 55.54Improved
complement 10% real data with XCube synthetic scenes (dense)segmentation network · SemanticKITTI val, densemIoU: 56.22 -> 53.75Hurt
complement 10% real data with our synthetic scenes (dense)segmentation network · SemanticKITTI val, densemIoU: 56.22 -> 61.73Improved
complement 10% real data with XCube synthetic scenes (LiDAR-simulated)segmentation network · SemanticKITTI val, LiDAR-simulatedmIoU: 45.58 -> 49.28Improved
add 75% extra synthetic scenes to full real training set (dense)segmentation network · SemanticKITTI val, densemIoU: 61.08 -> 64.14Improved
add 75% extra synthetic scenes to full real training set (LiDAR-simulated)segmentation network · SemanticKITTI val, LiDAR-simulatedmIoU: 55.59 -> 57.77Improved

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