Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
×
Sep 13, 2023 · Abstract:In this paper, we propose a novel training strategy called SupFusion, which provides an auxiliary feature level supervision for ...
In this paper, we propose a novel train- ing strategy called SupFusion, which provides an auxiliary feature level supervision for effective LiDAR-Camera fusion.
This is the official code of the paper "SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detection" - IranQin/SupFusion.
People also ask
The detector and optimizer settings including voxel size, epoch, and learning rate (LR) follow the open-sourced code and are shown in Tab. 1. Table 1: Detectors ...
In this paper, we propose a novel training strategy called SupFusion, which provides an auxiliary feature level supervision for effective LiDAR-Camera fusion ...
Oct 31, 2023 · To this end, in this paper we propose a supervised LiDAR-. Camera fusion method named SupFusion, to generate high- quality features and provide ...
A novel training strategy called SupFusion is proposed, which provides an auxiliary feature level supervision for effective LiDAR-Camera fusion and ...
In this paper, we propose a novel training strategy called SupFusion, which provides an auxiliary feature level supervision for effective LiDAR-Camera fusion ...
Jan 18, 2024 · In this research, we propose a new 3D object detector with a trustworthy depth estimation, dubbed BEVDepth, for camera-based ...
Sep 13, 2023 · In this paper, we propose a novel training strategy called SupFusion, whichprovides an auxiliary feature level supervision for effective ...