---
title: "MonoLaDN: Language-Guided DeNoising for Monocular 3D Object Detection"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.06282v1"
permalink: "https://feed.astralor.com/items/itm_fa5c212cffea5971127c4bd4"
published: "2026-11-04T10:22:16.000Z"
score: 59
channel: "tech"
tags: ["推理效率","多模态","MonoLaDN","Language-Guided DeNoising","Monocular","Object Detection Monocular","Recent","VLMs"]
---

# MonoLaDN: Language-Guided DeNoising for Monocular 3D Object Detection

## 速览

Monocular 3D object detection offers a low-cost route to 3D perception, but it remains fundamentally ill-posed, since depth must be inferred from a single view. Recent transformer-based detectors learn geometry purely f…

## 关键点

- Monocular 3D object detection offers a low-cost route to 3D perception, but it remains fundamentally ill-posed, since depth must be inferred from a single view.
- Recent transformer-based detectors learn geometry purely from image features and 3D box annotations, lacking the high-level semantic priors that vision-language models (VLMs) acquire from large-scale pretraining.
- VLMs offer such priors, but deploying one directly as a detector is impractical due to its heavy inference cost.

## 全文

Monocular 3D object detection offers a low-cost route to 3D perception, but it remains fundamentally ill-posed, since depth must be inferred from a single view. Recent transformer-based detectors learn geometry purely from image features and 3D box annotations, lacking the high-level semantic priors that vision-language models (VLMs) acquire from large-scale pretraining. VLMs offer such priors, but deploying one directly as a detector is impractical due to its heavy inference cost. We propose MonoLaDN, a language-guided denoising framework that transfers the geometric reasoning of a VLM into a monocular 3D detector while keeping the deployed model purely vision-based. During training, a frozen VLM produces structured reasoning about each object's occlusion, depth, dimension, and angle from the image and its ground-truth boxes. We encode this reasoning into queries, perturb them with noise, and train the detector to reconstruct the clean reasoning. Reconstructing the corrupted reasoning forces the detector's depth-guided features to internalize the VLM's geometric priors, so this knowledge remains available even after the reasoning path is discarded at inference, adding no latency or parameters to the deployed model. Experiments on KITTI 3D and nuScenes show that MonoLaDN consistently outperforms state-of-the-art detectors and generalizes well to new domains.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_fa5c212cffea5971127c4bd4