LIDAR Constrained NeRF on Outdoor Scenes
![Depth Map comparisons](/project/lidar-constrainted-nerf-on-outdoor-scenes/featured_hudd8a1d70b1d568f1ed361161b71d9a08_545898_720x0_resize_lanczos_3.png)
The goal of this project was to extend the NeRF architecture to make it work on outdoor scenes. In our case, we focused on autonomous driving scenarios with the KITTI-360 dataset. As baseline we built upon the DS-NeRF architecture and adapted it to work on LIDAR data and NDC space to deal with unbounded scenes. The main methods we have tried were:
- Depth Extrapolation + Inverse Depth Smoothness Loss as a regularizer
- Semantic Segmentation Loss to guide the optimization process
- Feature Loss (using a pre-trained VGG19 to create feature vectors)