no code implementations • 29 May 2023 • Yisu Zhang, Jianke Zhu, Lixiang Lin
Despite the promising results of multi-view reconstruction, the recent neural rendering-based methods, such as implicit surface rendering (IDR) and volume rendering (NeuS), not only incur a heavy computational burden on training but also have the difficulties in disentangling the geometric and appearance.
no code implementations • 26 Apr 2023 • Yisu Zhang, Jianke Zhu, Lixiang Lin
Comparing to the conventional deep learning-based multi-view stereo methods, our proposed RA-MVSNet approach obtains more complete reconstruction results by taking advantage of signed distance supervision.
Ranked #5 on Point Clouds on Tanks and Temples
no code implementations • CVPR 2023 • Yisu Zhang, Jianke Zhu, Lixiang Lin
It is essential to the textureless regions and surface boundary that cannot be properly reconstructed. To address this issue, we suggest to take advantage of point-to-surface distance so that the model is able to perceive a wider range of surfaces.
1 code implementation • 25 May 2022 • Lixiang Lin, Jianke Zhu, Yisu Zhang
Although having achieved the promising results on shape and color recovery through self-supervision, the multi-layer perceptrons-based methods usually suffer from heavy computational cost on learning the deep implicit surface representation.