Rethinking Feature Context in Learning Image-Guided Depth Completion
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING, ICANN 2023, PT III（2023）
Abstract
Depth completion (DC) is a classical computer vision task, which aims to estimate the 3D structure of the observed scene by utilizing the sparse depth from the Lidar and the RGB image from the camera. Treating DC as a regression task, most recent papers ignore the importance of feature representation. In this paper, we discuss the feature context in image-guided depth completion and propose a novel dual-arch feature extractor that includes a CNN branch and transformer branch. By combining the efficient CNN layers and effective transformer blocks, our proposed method achieves significant improvement compared with the baseline network. Experimental results and ablation study show the proposed approach can help existing DC methods perform better with limited extra computation.
MoreTranslated text
Key words
Depth completion,Feature context,Transformer
求助PDF
上传PDF
View via Publisher
AI Read Science
AI Summary
AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.
Example
Background
Key content
Introduction
Methods
Results
Related work
Fund
Key content
- Pretraining has recently greatly promoted the development of natural language processing (NLP)
- We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
- We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
- The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
- Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance
Upload PDF to Generate Summary
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Related Papers
RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completion
IEEE Transactions on Pattern Analysis and Machine Intelligence 2024
被引用20
Data Disclaimer
The page data are from open Internet sources, cooperative publishers and automatic analysis results through AI technology. We do not make any commitments and guarantees for the validity, accuracy, correctness, reliability, completeness and timeliness of the page data. If you have any questions, please contact us by email: report@aminer.cn
Chat Paper