434 citations · 681 across the 14 of their papers we have counts for
14 papers
Boosting Multi-View Stereo with Depth Foundation Model in the Absence of Real-World Labels
Jie Zhu, Bo Peng, Zhe Zhang +2
Learning-based Multi-View Stereo (MVS) methods have made remarkable progress in recent years. However, how to effectively train the network without using real-world labels remains…
Stereo Image Coding for Machines with Joint Visual Feature Compression
Dengchao Jin, Jianjun Lei, Bo Peng +3
2D image coding for machines (ICM) has achieved great success in coding efficiency, while less effort has been devoted to stereo image fields. To promote the efficiency of stereo i…
Multi-Projection Fusion and Refinement Network for Salient Object Detection in 360° Omnidirectional Image
Runmin Cong, Ke Huang, Jianjun Lei +3
Salient object detection (SOD) aims to determine the most visually attractive objects in an image. With the development of virtual reality technology, 360° omnidirectional image ha…
PSNet: Parallel Symmetric Network for Video Salient Object Detection
Runmin Cong, Weiyu Song, Jianjun Lei +3
For the video salient object detection (VSOD) task, how to excavate the information from the appearance modality and the motion modality has always been a topic of great concern. T…
Multi-View Stereo with Transformer
Jie Zhu, Bo Peng, Wanqing Li +3
This paper proposes a network, referred to as MVSTR, for Multi-View Stereo (MVS). It is built upon Transformer and is capable of extracting dense features with global context and 3…
Novel View Synthesis from a Single Image via Unsupervised learning
Bingzheng Liu, Jianjun Lei, Bo Peng +3
View synthesis aims to generate novel views from one or more given source views. Although existing methods have achieved promising performance, they usually require paired views of…