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

arXiv: https://arxiv.org/abs/2603.24294 · HTML: https://mlsanity.com/paper/2603.24294/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 34 of its 42 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Builds on (most cited first, 30 of 34)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [LVIS: A Dataset for Large Vocabulary Instance Segmentation](https://mlsanity.com/paper/1908.03195/) (2019)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks](https://mlsanity.com/paper/2006.10503/) (2020)
- [UniDepth: Universal Monocular Metric Depth Estimation](https://mlsanity.com/paper/2403.18913/) (2024)
- [Class-balanced Grouping and Sampling for Point Cloud 3D Object Detection](https://mlsanity.com/paper/1908.09492/) (2019)
- [BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework](https://mlsanity.com/paper/2205.13790/) (2022)
- [MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision](https://mlsanity.com/paper/2410.19115/) (2024)
- [A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting](https://mlsanity.com/paper/2312.03594/) (2023)
- [MVX-Net: Multimodal VoxelNet for 3D Object Detection](https://mlsanity.com/paper/1904.01649/) (2019)
- [Prometheus-Vision: Vision-Language Model as a Judge for Fine-Grained Evaluation](https://mlsanity.com/paper/2401.06591/) (2024)
- [DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models](https://mlsanity.com/paper/2308.06160/) (2023)
- [Virtual Sparse Convolution for Multimodal 3D Object Detection](https://mlsanity.com/paper/2303.02314/) (2023)
- [DiffuseMix: Label-Preserving Data Augmentation with Diffusion Models](https://mlsanity.com/paper/2405.14881/) (2024)
- [SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?](https://mlsanity.com/paper/2402.01832/) (2024)
- [Dataset Enhancement with Instance-Level Augmentations](https://mlsanity.com/paper/2406.08249/) (2024)
- [MLLM-as-a-Judge for Image Safety without Human Labeling](https://mlsanity.com/paper/2501.00192/) (2024)
- [3D Data Augmentation for Driving Scenes on Camera](https://mlsanity.com/paper/2303.10340/) (2023)
- [Reflectivity Is All You Need!: Advancing LiDAR Semantic Segmentation](https://mlsanity.com/paper/2403.13188/) (2024)
- [Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation](https://mlsanity.com/paper/2505.16985/) (2025)
- [Instance-Aware Repeat Factor Sampling for Long-Tailed Object Detection](https://mlsanity.com/paper/2305.08069/) (2023)
- [Self-Improving VLM Judges Without Human Annotations](https://mlsanity.com/paper/2512.05145/) (2025)
- [Text3DAug -- Prompted Instance Augmentation for LiDAR Perception](https://mlsanity.com/paper/2408.14253/) (2024)

## Abstract (arXiv)

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/.