no code implementations • 29 Mar 2022 • Xiaohe Ma, Yaxin Yu, Hongzhi Wu, Kun Zhou
A common, pre-trained latent transform module is also appended to each decoder, to offset the burden of the increased number of decoders.
no code implementations • ICCV 2021 • Kaizhang Kang, Cihui Xie, Ruisheng Zhu, Xiaohe Ma, Ping Tan, Hongzhi Wu, Kun Zhou
We present a novel framework to learn to convert the perpixel photometric information at each view into spatially distinctive and view-invariant low-level features, which can be plugged into existing multi-view stereo pipeline for enhanced 3D reconstruction.