no code implementations • 7 Aug 2023 • Xiang Feng, Kaizhang Kang, Fan Pei, Huakeng Ding, Jinjiang You, Ping Tan, Kun Zhou, Hongzhi Wu
We propose a novel framework to automatically learn to aggregate and transform photometric measurements from multiple unstructured views into spatially distinctive and view-invariant low-level features, which are fed to a multi-view stereo method to enhance 3D reconstruction.
no code implementations • 16 Mar 2022 • Kaizhang Kang, Chong Zeng, Hongzhi Wu, Kun Zhou
We present a novel framework to automatically learn to transform the differential cues from a stack of images densely captured with a rotational motion into spatially discriminative and view-invariant per-pixel features at each view.
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.