先验概率
计算机科学
计算机视觉
人工智能
杠杆(统计)
目标检测
对象(语法)
编码器
利用
稳健性(进化)
视觉对象识别的认知神经科学
模式识别(心理学)
特征(语言学)
对象模型
可视化
特征提取
几何造型
Lift(数据挖掘)
实体造型
钥匙(锁)
三维重建
探测器
空间关系
姿势
偏移量(计算机科学)
几何数据分析
语义特征
软件部署
观察员(物理)
掉期(金融)
作者
Yang Cao,Feize Wu,Dave Zhenyu Chen,Yingji Zhong,Lanqing Hong,Dan Xu
标识
DOI:10.48550/arxiv.2603.00912
摘要
Current multi-view indoor 3D object detectors rely on sensor geometry that is costly to obtain (i.e., precisely calibrated multi-view camera poses) to fuse multi-view information into a global scene representation, limiting deployment in real-world scenes. We target a more practical setting: Sensor-Geometry-Free (SG-Free) multi-view indoor 3D object detection, where there are no sensor-provided geometric inputs (multi-view poses or depth). Recent Visual Geometry Grounded Transformer (VGGT) shows that strong 3D cues can be inferred directly from images. Building on this insight, we present VGGT-Det, the first framework tailored for SG-Free multi-view indoor 3D object detection. Rather than merely consuming VGGT predictions, our method integrates VGGT encoder into a transformer-based pipeline. To effectively leverage both the semantic and geometric priors from inside VGGT, we introduce two novel key components: (i) Attention-Guided Query Generation (AG): exploits VGGT attention maps as semantic priors to initialize object queries, improving localization by focusing on object regions while preserving global spatial structure; (ii) Query-Driven Feature Aggregation (QD): a learnable See-Query interacts with object queries to 'see' what they need, and then dynamically aggregates multi-level geometric features across VGGT layers that progressively lift 2D features into 3D. Experiments show that VGGT-Det significantly surpasses the best-performing method in the SG-Free setting by 4.4 and 8.6 mAP@0.25 on ScanNet and ARKitScenes, respectively. Ablation study shows that VGGT's internally learned semantic and geometric priors can be effectively leveraged by our AG and QD.
科研通智能强力驱动
Strongly Powered by AbleSci AI