Hybrid voxel-and surface-guided 3D surface reconstruction

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

Neural 3D Reconstruction in the Wild

We introduce a new method that enables efficient and accurate surface reconstruction from photocollections in the presence of varying illumination.

To achieve this, we propose a hybrid voxel-and surface-guided sampling technique that allows for more efficient ray sampling around surfaces and leads to significant improvements in reconstruction quality.

We perform extensive experiments, demonstrating that our approach surpasses both classical and neural reconstruction methods on a wide variety of metrics.

We present a new benchmark and protocol for evaluating reconstruction performance on such in-the-wild scenes.

Authors

Jiaming Sun, Xi Chen, Qianqian Wang, Zhengqi Li, Hadar Averbuch-Elor, Xiaowei Zhou, Noah Snavely

◐ Latest Activity

◐ Recommended Follows