7 citations · 8 across the 4 of their papers we have counts for
4 papers
ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion
Jiayu Yang, Ziang Cheng, Yunfei Duan +2
Given a single image of a 3D object, this paper proposes a novel method (named ConsistNet) that is able to generate multiple images of the same object, as if seen they are captured…
Stereo Matching in Time: 100+ FPS Video Stereo Matching for Extended Reality
Ziang Cheng, Jiayu Yang, Hongdong Li
Real-time Stereo Matching is a cornerstone algorithm for many Extended Reality (XR) applications, such as indoor 3D understanding, video pass-through, and mixed-reality games. Desp…
Parametric Depth Based Feature Representation Learning for Object Detection and Segmentation in Bird's Eye View
Jiayu Yang, Enze Xie, Miaomiao Liu +1
Recent vision-only perception models for autonomous driving achieved promising results by encoding multi-view image features into Bird's-Eye-View (BEV) space. A critical step and t…
Butterfly: Multiple Reference Frames Feature Propagation Mechanism for Neural Video Compression
Feng Wang, Haihang Ruan, Fei Xiong +3
Using more reference frames can significantly improve the compression efficiency in neural video compression. However, in low-latency scenarios, most existing neural video compress…