Neural 3d reconstruction in the wild
ACM SIGGRAPH 2022 conference proceedings, 2022•dl.acm.org
We are witnessing an explosion of neural implicit representations in computer vision and
graphics. Their applicability has recently expanded beyond tasks such as shape generation
and image-based rendering to the fundamental problem of image-based 3D reconstruction.
However, existing methods typically assume constrained 3D environments with constant
illumination captured by a small set of roughly uniformly distributed cameras. We introduce a
new method that enables efficient and accurate surface reconstruction from Internet photo …
graphics. Their applicability has recently expanded beyond tasks such as shape generation
and image-based rendering to the fundamental problem of image-based 3D reconstruction.
However, existing methods typically assume constrained 3D environments with constant
illumination captured by a small set of roughly uniformly distributed cameras. We introduce a
new method that enables efficient and accurate surface reconstruction from Internet photo …
We are witnessing an explosion of neural implicit representations in computer vision and graphics. Their applicability has recently expanded beyond tasks such as shape generation and image-based rendering to the fundamental problem of image-based 3D reconstruction. However, existing methods typically assume constrained 3D environments with constant illumination captured by a small set of roughly uniformly distributed cameras. We introduce a new method that enables efficient and accurate surface reconstruction from Internet photo collections 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. Further, we present a new benchmark and protocol for evaluating reconstruction performance on such in-the-wild scenes. We perform extensive experiments, demonstrating that our approach surpasses both classical and neural reconstruction methods on a wide variety of metrics. Code and data will be made available at https://zju3dv.github.io/neuralrecon-w.
ACM Digital Library
以上显示的是最相近的搜索结果。 查看全部搜索结果