TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Shaoqing, Li, Fang, Huang, Peixiang, Song, Ziying, Yang, Zhi-Xin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913629299802112
author Xu, Shaoqing
Li, Fang
Huang, Peixiang
Song, Ziying
Yang, Zhi-Xin
author_facet Xu, Shaoqing
Li, Fang
Huang, Peixiang
Song, Ziying
Yang, Zhi-Xin
contents Accurate multi-view 3D object detection is essential for applications such as autonomous driving. Researchers have consistently aimed to leverage LiDAR's precise spatial information to enhance camera-based detectors through methods like depth supervision and bird-eye-view (BEV) feature distillation. However, existing approaches often face challenges due to the inherent differences between LiDAR and camera data representations. In this paper, we introduce the TiGDistill-BEV, a novel approach that effectively bridges this gap by leveraging the strengths of both sensors. Our method distills knowledge from diverse modalities(e.g., LiDAR) as the teacher model to a camera-based student detector, utilizing the Target Inner-Geometry learning scheme to enhance camera-based BEV detectors through both depth and BEV features by leveraging diverse modalities. Specially, we propose two key modules: an inner-depth supervision module to learn the low-level relative depth relations within objects which equips detectors with a deeper understanding of object-level spatial structures, and an inner-feature BEV distillation module to transfer high-level semantics of different key points within foreground targets. To further alleviate the domain gap, we incorporate both inter-channel and inter-keypoint distillation to model feature similarity. Extensive experiments on the nuScenes benchmark demonstrate that TiGDistill-BEV significantly boosts camera-based only detectors achieving a state-of-the-art with 62.8% NDS and surpassing previous methods by a significant margin. The codes is available at: https://github.com/Public-BOTs/TiGDistill-BEV.git.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20911
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation
Xu, Shaoqing
Li, Fang
Huang, Peixiang
Song, Ziying
Yang, Zhi-Xin
Computer Vision and Pattern Recognition
Accurate multi-view 3D object detection is essential for applications such as autonomous driving. Researchers have consistently aimed to leverage LiDAR's precise spatial information to enhance camera-based detectors through methods like depth supervision and bird-eye-view (BEV) feature distillation. However, existing approaches often face challenges due to the inherent differences between LiDAR and camera data representations. In this paper, we introduce the TiGDistill-BEV, a novel approach that effectively bridges this gap by leveraging the strengths of both sensors. Our method distills knowledge from diverse modalities(e.g., LiDAR) as the teacher model to a camera-based student detector, utilizing the Target Inner-Geometry learning scheme to enhance camera-based BEV detectors through both depth and BEV features by leveraging diverse modalities. Specially, we propose two key modules: an inner-depth supervision module to learn the low-level relative depth relations within objects which equips detectors with a deeper understanding of object-level spatial structures, and an inner-feature BEV distillation module to transfer high-level semantics of different key points within foreground targets. To further alleviate the domain gap, we incorporate both inter-channel and inter-keypoint distillation to model feature similarity. Extensive experiments on the nuScenes benchmark demonstrate that TiGDistill-BEV significantly boosts camera-based only detectors achieving a state-of-the-art with 62.8% NDS and surpassing previous methods by a significant margin. The codes is available at: https://github.com/Public-BOTs/TiGDistill-BEV.git.
title TiGDistill-BEV: Multi-view BEV 3D Object Detection via Target Inner-Geometry Learning Distillation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.20911