后处理 - 标签 - Zhaoylee's Blogs https://zhaoylee.github.io/Blogs_lovelt/tags/%E5%90%8E%E5%A4%84%E7%90%86/ 后处理 - 标签 - Zhaoylee's Blogs Hugo -- gohugo.iozh-CNSun, 15 Mar 2026 21:14:36 +0800 MonoXiver： Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver https://zhaoylee.github.io/Blogs_lovelt/posts/monoxiver--monocular-3d-object-detection-with-bounding-box-denoising-in-3d-by-perceivermonocular-3d-object-detection-with-bounding-box-denoising-in-3d-by-perceiver/ Sun, 15 Mar 2026 21:14:36 +0800 zhaoylee https://zhaoylee.github.io/Blogs_lovelt/posts/monoxiver--monocular-3d-object-detection-with-bounding-box-denoising-in-3d-by-perceivermonocular-3d-object-detection-with-bounding-box-denoising-in-3d-by-perceiver/

🏛️ 会议/期刊：ICCV
📅 发表年份：2023
💻 开源代码：Xianpeng919/monoxiver (ICCV'23)
📄 论文题目：Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver

这篇发表于 ICCV 2023 的论文 《Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver》(简称 MonoXiver)，提供了一个非常经典且极具工程价值的“自上而下（Top-down）”纠错思路。它并没有试图发明一种全新的主干网络，而是设计了一个强大的“插件”，专门用来拯救那些定位不准的预测框。

]]> DIGGING INTO OUTPUT REPRESENTATION FOR MONOCULAR 3D OBJECT DETECTION https://zhaoylee.github.io/Blogs_lovelt/posts/digging-into-output-representation-for-monocular-3d-object-detection/ Fri, 13 Mar 2026 15:27:43 +0800 zhaoylee https://zhaoylee.github.io/Blogs_lovelt/posts/digging-into-output-representation-for-monocular-3d-object-detection/ 通过深度采样的方式，一个预测得到多个预测位置，其他位置的score 低于当前预测，增加了Recall；]]>