Thousands of images and videos are collected from construction projects during
construction. These contain valuable data that, if harnessed efficiently, can help automate or …

Recent years have witnessed enormous progress in AI-related fields such as computer
vision, machine learning, and autonomous vehicles. As with any rapidly growing field, it …

Abstract We present Block-NeRF, a variant of Neural Radiance Fields that can represent
large-scale environments. Specifically, we demonstrate that when scaling NeRF to render …

Purely MLP-based neural radiance fields (NeRF-based methods) often suffer from
underfitting with blurred renderings on large-scale scenes due to limited model capacity …

Existing NeRF-based methods for large scene reconstruction often have limitations in visual
quality and rendering speed. While the recent 3D Gaussian Splatting works well on small …

We present a benchmark for image-based 3D reconstruction. The benchmark sequences
were acquired outside the lab, in realistic conditions. Ground-truth data was captured using …

Abstract Incremental Structure-from-Motion is a prevalent strategy for 3D reconstruction from
unordered image collections. While incremental reconstruction systems have tremendously …

Online reconstruction based on RGB-D sequences has thus far been restrained to relatively
slow camera motions (< 1m/s). Under very fast camera motion (eg, 3m/s), the reconstruction …

We present a learnt system for multi-view stereopsis. In contrast to recent learning based
methods for 3D reconstruction, we leverage the underlying 3D geometry of the problem …

Training robust deep video representations has proven to be much more challenging than
learning deep image representations. This is in part due to the enormous size of raw video …