ALIGN: Advanced Query Initialization with LiDAR-Image Guidance for Occlusion-Robust 3D Object Detection

• URL: http://arxiv.org/abs/2512.18187v1
• Date: Sat, 20 Dec 2025 02:51:00 GMT
• Title: ALIGN: Advanced Query Initialization with LiDAR-Image Guidance for Occlusion-Robust 3D Object Detection
• Authors: Janghyun Baek, Mincheol Chang, Seokha Moon, Seung Joon Lee, Jinkyu Kim,
• Abstract summary: We propose ALIGN, a novel approach for object-aware query initialization.<n>Our model consists of three key components: (i) Occlusion-aware Center Estimation (OCE), which integrates LiDAR geometry and image semantics.<n>Our experiments on the nuScenes benchmark demonstrate that ALIGN consistently improves performance across multiple state-of-the-art detectors.
• Score: 16.336860116706088
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent query-based 3D object detection methods using camera and LiDAR inputs have shown strong performance, but existing query initialization strategies,such as random sampling or BEV heatmap-based sampling, often result in inefficient query usage and reduced accuracy, particularly for occluded or crowded objects. To address this limitation, we propose ALIGN (Advanced query initialization with LiDAR and Image GuidaNce), a novel approach for occlusion-robust, object-aware query initialization. Our model consists of three key components: (i) Occlusion-aware Center Estimation (OCE), which integrates LiDAR geometry and image semantics to estimate object centers accurately (ii) Adaptive Neighbor Sampling (ANS), which generates object candidates from LiDAR clustering and supplements each object by sampling spatially and semantically aligned points around it and (iii) Dynamic Query Balancing (DQB), which adaptively balances queries between foreground and background regions. Our extensive experiments on the nuScenes benchmark demonstrate that ALIGN consistently improves performance across multiple state-of-the-art detectors, achieving gains of up to +0.9 mAP and +1.2 NDS, particularly in challenging scenes with occlusions or dense crowds. Our code will be publicly available upon publication.

Related papers

• LDRFusion: A LiDAR-Dominant multimodal refinement framework for 3D object detection [5.820124526272312]
  Existing LiDAR-Camera fusion methods have achieved strong results in 3D object detection.<n>We propose LDRFusion, a novel Lidar-dominant two-stage refinement framework for multi-sensor fusion.<n>Our framework consistently achieves strong performance across multiple categories and difficulty levels.
  arXiv  Detail & Related papers  (2025-07-22T04:35:52Z)
• RaCFormer: Towards High-Quality 3D Object Detection via Query-based Radar-Camera Fusion [58.77329237533034]
  We propose a Radar-Camera fusion transformer (RaCFormer) to boost the accuracy of 3D object detection.<n>RaCFormer achieves superior results of 64.9% mAP and 70.2% on nuScenes datasets.
  arXiv  Detail & Related papers  (2024-12-17T09:47:48Z)
• STONE: A Submodular Optimization Framework for Active 3D Object Detection [20.54906045954377]
  Key requirement for training an accurate 3D object detector is the availability of a large amount of LiDAR-based point cloud data. This paper proposes a unified active 3D object detection framework, for greatly reducing the labeling cost of training 3D object detectors.
  arXiv  Detail & Related papers  (2024-10-04T20:45:33Z)
• SEED: A Simple and Effective 3D DETR in Point Clouds [72.74016394325675]
  We argue that the main challenges are challenging due to the high sparsity and uneven distribution of point clouds. We propose a simple and effective 3D DETR method (SEED) for detecting 3D objects from point clouds.
  arXiv  Detail & Related papers  (2024-07-15T14:21:07Z)
• Find n' Propagate: Open-Vocabulary 3D Object Detection in Urban Environments [67.83787474506073]
  We tackle the limitations of current LiDAR-based 3D object detection systems. We introduce a universal textscFind n' Propagate approach for 3D OV tasks. We achieve up to a 3.97-fold increase in Average Precision (AP) for novel object classes.
  arXiv  Detail & Related papers  (2024-03-20T12:51:30Z)
• Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection [54.041049052843604]
  We present STEMD, a novel end-to-end framework that enhances the DETR-like paradigm for multi-frame 3D object detection. First, to model the inter-object spatial interaction and complex temporal dependencies, we introduce the spatial-temporal graph attention network. Finally, it poses a challenge for the network to distinguish between the positive query and other highly similar queries that are not the best match.
  arXiv  Detail & Related papers  (2023-07-01T13:53:14Z)
• Exploring Active 3D Object Detection from a Generalization Perspective [58.597942380989245]
  Uncertainty-based active learning policies fail to balance the trade-off between point cloud informativeness and box-level annotation costs. We propose textscCrb, which hierarchically filters out the point clouds of redundant 3D bounding box labels. Experiments show that the proposed approach outperforms existing active learning strategies.
  arXiv  Detail & Related papers  (2023-01-23T02:43:03Z)
• D-Align: Dual Query Co-attention Network for 3D Object Detection Based on Multi-frame Point Cloud Sequence [8.21339007493213]
  Conventional 3D object detectors detect objects using a set of points acquired over a fixed duration. Recent studies have shown that the performance of object detection can be further enhanced by utilizing point cloud sequences. We propose D-Align, which can effectively produce strong bird's-eye-view (BEV) features by aligning and aggregating the features obtained from a sequence of point sets.
  arXiv  Detail & Related papers  (2022-09-30T20:41:25Z)
• CMR3D: Contextualized Multi-Stage Refinement for 3D Object Detection [57.44434974289945]
  We propose Contextualized Multi-Stage Refinement for 3D Object Detection (CMR3D) framework. Our framework takes a 3D scene as input and strives to explicitly integrate useful contextual information of the scene. In addition to 3D object detection, we investigate the effectiveness of our framework for the problem of 3D object counting.
  arXiv  Detail & Related papers  (2022-09-13T05:26:09Z)
• SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection [78.90102636266276]
  We propose a novel set abstraction method named Semantics-Augmented Set Abstraction (SASA) Based on the estimated point-wise foreground scores, we then propose a semantics-guided point sampling algorithm to help retain more important foreground points during down-sampling. In practice, SASA shows to be effective in identifying valuable points related to foreground objects and improving feature learning for point-based 3D detection.
  arXiv  Detail & Related papers  (2022-01-06T08:54:47Z)
• IAFA: Instance-aware Feature Aggregation for 3D Object Detection from a Single Image [37.83574424518901]
  3D object detection from a single image is an important task in Autonomous Driving. We propose an instance-aware approach to aggregate useful information for improving the accuracy of 3D object detection.
  arXiv  Detail & Related papers  (2021-03-05T05:47:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.