PulseAugur
LIVE 06:42:50
research · [2 sources] ·
0
research

New CARD dataset offers dense 3D reconstruction for autonomous driving on rough terrain

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 2 sources

Researchers have introduced CARD, a new multi-modal automotive dataset designed for dense 3D reconstruction in challenging road conditions. Unlike existing datasets that focus on well-paved roads, CARD provides quasi-dense 3D ground truth for irregular surfaces like potholes and off-road segments. The dataset includes synchronized data from stereo cameras, LiDARs, and motion sensors, spanning approximately 110 km across Germany and Italy. AI

Summary written by gemini-2.5-flash-lite from 2 sources. How we write summaries →

IMPACT Provides a new benchmark dataset for improving depth estimation and perception in autonomous driving systems operating on varied terrain.

RANK_REASON This is a research paper introducing a new dataset for computer vision tasks.

Read on arXiv cs.CV →

COVERAGE [2]

  1. arXiv cs.CV TIER_1 · Gasser Elazab, Frank Neuhaus, Tilman Ko{\ss}, Malte Splietker, Aditya Date, Michael Unterreiner, Maximilian Jansen, Olaf Hellwich ·

    CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography

    arXiv:2605.05014v1 Announce Type: new Abstract: Autonomous driving must operate across diverse surfaces to enable safe mobility. However, most driving datasets are captured on well-paved flat roads. Moreover, recent driving datasets primarily provide sparse LiDAR ground truth for…

  2. arXiv cs.CV TIER_1 · Olaf Hellwich ·

    CARD: A Multi-Modal Automotive Dataset for Dense 3D Reconstruction in Challenging Road Topography

    Autonomous driving must operate across diverse surfaces to enable safe mobility. However, most driving datasets are captured on well-paved flat roads. Moreover, recent driving datasets primarily provide sparse LiDAR ground truth for images, which is insufficient for assessing fin…

RELATED ENTITIES

RELATED TOPICS