Research

Paper

TESTING March 25, 2026

VERIA: Verification-Centric Multimodal Instance Augmentation for Long-Tailed 3D Object Detection

Authors

Jumin Lee, Siyeong Lee, Namil Kim, Sung-Eui Yoon

Abstract

Long-tail distributions in driving datasets pose a fundamental challenge for 3D perception, as rare classes exhibit substantial intra-class diversity yet available samples cover this variation space only sparsely. Existing instance augmentation methods based on copy-paste or asset libraries improve rare-class exposure but are often limited in fine-grained diversity and scene-context placement. We propose VERIA, an image-first multimodal augmentation framework that synthesizes synchronized RGB--LiDAR instances using off-the-shelf foundation models and curates them with sequential semantic and geometric verification. This verification-centric design tends to select instances that better match real LiDAR statistics while spanning a wider range of intra-class variation. Stage-wise yield decomposition provides a log-based diagnostic of pipeline reliability. On nuScenes and Lyft, VERIA improves rare-class 3D object detection in both LiDAR-only and multimodal settings. Our code is available at https://sgvr.kaist.ac.kr/VERIA/.

Metadata

arXiv ID: 2603.24294
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-25
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.24294v1</id>\n    <title>VERIA: Verification-Centric Multimodal Instance Augmentation for Long-Tailed 3D Object Detection</title>\n    <updated>2026-03-25T13:30:38Z</updated>\n    <link href='https://arxiv.org/abs/2603.24294v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.24294v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Long-tail distributions in driving datasets pose a fundamental challenge for 3D perception, as rare classes exhibit substantial intra-class diversity yet available samples cover this variation space only sparsely. Existing instance augmentation methods based on copy-paste or asset libraries improve rare-class exposure but are often limited in fine-grained diversity and scene-context placement. We propose VERIA, an image-first multimodal augmentation framework that synthesizes synchronized RGB--LiDAR instances using off-the-shelf foundation models and curates them with sequential semantic and geometric verification. This verification-centric design tends to select instances that better match real LiDAR statistics while spanning a wider range of intra-class variation. Stage-wise yield decomposition provides a log-based diagnostic of pipeline reliability. On nuScenes and Lyft, VERIA improves rare-class 3D object detection in both LiDAR-only and multimodal settings. Our code is available at https://sgvr.kaist.ac.kr/VERIA/.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-25T13:30:38Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Jumin Lee</name>\n    </author>\n    <author>\n      <name>Siyeong Lee</name>\n    </author>\n    <author>\n      <name>Namil Kim</name>\n    </author>\n    <author>\n      <name>Sung-Eui Yoon</name>\n    </author>\n  </entry>"
}