归档

2026  14

三月  14

OCM3D: Object-Centric Monocular 3D Object Detection

📅 发表于 2026-03-16  |  📁 CenterNet-Based, 即插即用型  |  🏷️ 置信度解耦, 3D-2D投影对齐, 投影验证

LR3D: Improving Distant 3D Object Detection Using 2D Box Supervision

📅 发表于 2026-03-15  |  📁 CenterNet-Based, 即插即用型  |  🏷️ 长距离感知, 隐式投影

StreamPETR-QAF2D：Enhancing 3D Object Detection with 2D Detection-Guided Query Anchors

📅 发表于 2026-03-15  |  📁 Transformer-Based  |  🏷️ 2D引导3D, 投影验证

OBMO: One Bounding Box Multiple Objects for Monocular 3D Object Detection

📅 发表于 2026-03-15  |  📁 即插即用型  |  🏷️ 深度模糊, 软标签训练

Open Vocabulary Monocular 3D Object Detection

📅 发表于 2026-03-15  |  📁 开放集M3OD  |  🏷️ 开放词汇检测OVD, VLM, 额外的深度模型

MonoXiver： Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver

📅 发表于 2026-03-15  |  📁 即插即用型, CenterNet-Based  |  🏷️ 边界框去噪, 跨模态特征融合, 后处理

PLOT: Pseudo-Labeling via Object Tracking for Monocular 3D Object Detection

📅 发表于 2026-03-15  |  📁 CenterNet-Based, Transformer-Based, 即插即用型  |  🏷️ 额外的深度模型, 伪标签生成, 时序聚合

Difficulty-Aware Label-Guided Denoising for Monocular 3D Object Detection

📅 发表于 2026-03-15  |  📁 Transformer-Based  |  🏷️ 查询去噪

Mono3DV: Monocular 3D Object Detection with 3D-Aware Bipartite Matching and Variational Query DeNoising

📅 发表于 2026-03-15  |  📁 Transformer-Based  |  🏷️ 变分去噪

Object-Scene-Camera Decomposition and Recomposition for Data-Efficient Monocular 3D Object Detection

📅 发表于 2026-03-15  |  📁 即插即用型  |  🏷️ 数据增强, 部分标注

SpikeSMOKE: Spiking Neural Networks for Monocular 3D Object Detection with Cross-Scale Gated Coding

📅 发表于 2026-03-15  |  📁 CenterNet-Based  |  🏷️ 轻量化, 跨尺度, 门控

SPAN: Spatial-Projection Alignment for Monocular 3D Object Detection

📅 发表于 2026-03-15  |  📁 Transformer-Based  |  🏷️ 协同约束, 3D-2D投影对齐

DIGGING INTO OUTPUT REPRESENTATION FOR MONOCULAR 3D OBJECT DETECTION

📅 发表于 2026-03-13  |  🕒 更新于 2026-03-16  |  📁 即插即用型  |  🏷️ 一对多, 深度采样, 后处理

MonoCT: Overcoming Monocular 3D Detection Domain Shift with Consistent Teacher Models

📅 发表于 2026-03-12  |  🕒 更新于 2026-03-16  |  📁 CenterNet-Based  |  🏷️ 车载、路边、无人机, 额外的模型, 多深度集成, 无监督