paper-with-me

Papers

GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection

2023-10-12 · ICCV 2023 1 · Ziying Song, Haiyue Wei, Lin Bai, Lei Yang, Caiyan Jia

LiDAR and cameras are complementary sensors for 3D object detection in autonomous driving. However, it is challenging to explore the unnatural interaction between point clouds and images, and the critical factor is how to conduct feature alignment of heterogeneous modalities. Currently, many methods achieve feature alignment by projection calibration only, without considering the problem of coordinate conversion accuracy errors between sensors, leading to sub-optimal performance. In this paper, we present GraphAlign, a more accurate feature alignment strategy for 3D object detection by graph matching. Specifically, we fuse image features from a semantic segmentation encoder in the image branch and point cloud features from a 3D Sparse CNN in the LiDAR branch. To save computation, we construct the nearest neighbor relationship by calculating Euclidean distance within the subspaces that are divided into the point cloud features. Through the projection calibration between the image and point cloud, we project the nearest neighbors of point cloud features onto the image features. Then by matching the nearest neighbors with a single point cloud to multiple images, we search for a more appropriate feature alignment. In addition, we provide a self-attention module to enhance the weights of significant relations to fine-tune the feature alignment between heterogeneous modalities. Extensive experiments on nuScenes benchmark demonstrate the effectiveness and efficiency of our GraphAlign.

📄 PDF Abstract BibTeX arXiv:2310.08261

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object DetectionAutonomous DrivingGraph Matchingobject-detectionObject DetectionSemantic Segmentation

Similar Papers 제목 키워드 기반

GraphAlign: Pretraining One Graph Neural Network on Multiple Graphs via Feature Alignment

2024-06-05 · Zhenyu Hou, Haozhan Li, Yukuo Cen, Jie Tang 외

Graph self-supervised learning (SSL) holds considerable promise for mining and learning with graph-structured data. Yet, a significant challenge in graph SSL lies in the feature discrepancy among graphs across different …

Graph Neural NetworkSelf-Supervised Learning

Can Modifying Data Address Graph Domain Adaptation?

2024-07-27 · Renhong Huang, Jiarong Xu, Xin Jiang, Ruichuan An 외

Graph neural networks (GNNs) have demonstrated remarkable success in numerous graph analytical tasks. Yet, their effectiveness is often compromised in real-world scenarios due to distribution shifts, limiting their capac…

Domain AdaptationGRAPH DOMAIN ADAPTATIONTransfer Learning

Enhancing Visual Forced Alignment with Local Context-Aware Feature Extraction and Multi-Task Learning

2025-03-05 · Yi He, Lei Yang, Shilin Wang

This paper introduces a novel approach to Visual Forced Alignment (VFA), aiming to accurately synchronize utterances with corresponding lip movements, without relying on audio cues. We propose a novel VFA approach that i…

Multi-Task Learning

Morphology-Aware KOA Classification: Integrating Graph Priors with Vision Models

2025-10-20 · Marouane Tliba, Mohamed Amine Kerkouri, Yassine Nasser, Nour Aburaed 외 arxiv

Knee osteoarthritis (KOA) diagnosis from radiographs remains challenging due to the subtle morphological details that standard deep learning models struggle to capture effectively. We propose a novel multimodal framework…

GraphBEV: Towards Robust BEV Feature Alignment for Multi-Modal 3D Object Detection

2024-03-18 · Ziying Song, Lei Yang, Shaoqing Xu, Lin Liu 외

Integrating LiDAR and camera information into Bird's-Eye-View (BEV) representation has emerged as a crucial aspect of 3D object detection in autonomous driving. However, existing methods are susceptible to the inaccurate…

3D Object DetectionAutonomous DrivingDepth EstimationGraph Matching+2