# Attention-Based Depth Distillation with 3D-Aware Positional Encoding for Monocular 3D Object Detection

arXiv: https://arxiv.org/abs/2211.16779 · HTML: https://mlsanity.com/paper/2211.16779/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 47 of its 64 references that are in the map.
- First posted on arXiv 30 Nov 2022.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 47)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [PointPillars: Fast Encoders for Object Detection from Point Clouds](https://mlsanity.com/paper/1812.05784/) (2018)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud](https://mlsanity.com/paper/1812.04244/) (2018)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1812.07179/) (2018)
- [PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images](https://mlsanity.com/paper/2206.01256/) (2022)
- [A Comprehensive Overhaul of Feature Distillation](https://mlsanity.com/paper/1904.01866/) (2019)
- [Categorical Depth Distribution Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.01100/) (2021)
- [Structured Knowledge Distillation for Dense Prediction](https://mlsanity.com/paper/1903.04197/) (2019)
- [3D Bounding Box Estimation Using Deep Learning and Geometry](https://mlsanity.com/paper/1612.00496/) (2016)
- [M3D-RPN: Monocular 3D Region Proposal Network for Object Detection](https://mlsanity.com/paper/1907.06038/) (2019)
- [Is Pseudo-Lidar needed for Monocular 3D Object detection?](https://mlsanity.com/paper/2108.06417/) (2021)
- [Distilling Object Detectors with Fine-grained Feature Imitation](https://mlsanity.com/paper/1906.03609/) (2019)
- [Objects are Different: Flexible Monocular 3D Object Detection](https://mlsanity.com/paper/2104.02323/) (2021)
- [Learning Depth-Guided Convolutions for Monocular 3D Object Detection](https://mlsanity.com/paper/1912.04799/) (2019)
- [Stereo R-CNN based 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/1902.09738/) (2019)
- [Geometry Uncertainty Projection Network for Monocular 3D Object Detection](https://mlsanity.com/paper/2107.13774/) (2021)
- [RTM3D: Real-time Monocular 3D Detection from Object Keypoints for Autonomous Driving](https://mlsanity.com/paper/2001.03343/) (2020)
- [End-to-end people detection in crowded scenes](https://mlsanity.com/paper/1506.04878/) (2015)
- [Delving into Localization Errors for Monocular 3D Object Detection](https://mlsanity.com/paper/2103.16237/) (2021)
- [Accurate Monocular Object Detection via Color-Embedded 3D Reconstruction for Autonomous Driving](https://mlsanity.com/paper/1903.11444/) (2019)
- [Kinematic 3D Object Detection in Monocular Video](https://mlsanity.com/paper/2007.09548/) (2020)
- [Monocular 3D Object Detection with Pseudo-LiDAR Point Cloud](https://mlsanity.com/paper/1903.09847/) (2019)
- [Rethinking Pseudo-LiDAR Representation](https://mlsanity.com/paper/2008.04582/) (2020)

## Built on by (most cited first, 7 of 7)

- [MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders](https://mlsanity.com/paper/2405.07696/) (2024)
- [MonoTAKD: Teaching Assistant Knowledge Distillation for Monocular 3D Object Detection](https://mlsanity.com/paper/2404.04910/) (2024)
- [Depth-discriminative Metric Learning for Monocular 3D Object Detection](https://mlsanity.com/paper/2401.01075/) (2024)
- [Multi-task Learning for Real-time Autonomous Driving Leveraging Task-adaptive Attention Generator](https://mlsanity.com/paper/2403.03468/) (2024)
- [Knowledge Distillation from 3D to Bird's-Eye-View for LiDAR Semantic Segmentation](https://mlsanity.com/paper/2304.11393/) (2023)
- [LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection](https://mlsanity.com/paper/2512.05663/) (2025)
- [Selective Transfer Learning of Cross-Modality Distillation for Monocular 3D Object Detection](https://mlsanity.com/paper/2603.07464/) (2026)

## Abstract (arXiv)

Monocular 3D object detection is a low-cost but challenging task, as it requires generating accurate 3D localization solely from a single image input. Recent developed depth-assisted methods show promising results by using explicit depth maps as intermediate features, which are either precomputed by monocular depth estimation networks or jointly evaluated with 3D object detection. However, inevitable errors from estimated depth priors may lead to misaligned semantic information and 3D localization, hence resulting in feature smearing and suboptimal predictions. To mitigate this issue, we propose ADD, an Attention-based Depth knowledge Distillation framework with 3D-aware positional encoding. Unlike previous knowledge distillation frameworks that adopt stereo- or LiDAR-based teachers, we build up our teacher with identical architecture as the student but with extra ground-truth depth as input. Credit to our teacher design, our framework is seamless, domain-gap free, easily implementable, and is compatible with object-wise ground-truth depth. Specifically, we leverage intermediate features and responses for knowledge distillation. Considering long-range 3D dependencies, we propose 3D-aware self-attention and target-aware cross-attention modules for student adaptation. Extensive experiments are performed to verify the effectiveness of our framework on the challenging KITTI 3D object detection benchmark. We implement our framework on three representative monocular detectors, and we achieve state-of-the-art performance with no additional inference computational cost relative to baseline models. Our code is available at https://github.com/rockywind/ADD.