NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds
This addresses view synthesis for indoor navigation, but it is incremental as it builds on existing NeRF methods with specific enhancements.
The paper tackles the problem of free navigation in indoor scenes using neural radiance fields (NeRF), which struggle with novel views far from training data, by introducing NeRFVS with geometry scaffolds and loss functions to improve learning, resulting in outperforming state-of-the-art methods quantitatively and qualitatively.
We present NeRFVS, a novel neural radiance fields (NeRF) based method to enable free navigation in a room. NeRF achieves impressive performance in rendering images for novel views similar to the input views while suffering for novel views that are significantly different from the training views. To address this issue, we utilize the holistic priors, including pseudo depth maps and view coverage information, from neural reconstruction to guide the learning of implicit neural representations of 3D indoor scenes. Concretely, an off-the-shelf neural reconstruction method is leveraged to generate a geometry scaffold. Then, two loss functions based on the holistic priors are proposed to improve the learning of NeRF: 1) A robust depth loss that can tolerate the error of the pseudo depth map to guide the geometry learning of NeRF; 2) A variance loss to regularize the variance of implicit neural representations to reduce the geometry and color ambiguity in the learning procedure. These two loss functions are modulated during NeRF optimization according to the view coverage information to reduce the negative influence brought by the view coverage imbalance. Extensive results demonstrate that our NeRFVS outperforms state-of-the-art view synthesis methods quantitatively and qualitatively on indoor scenes, achieving high-fidelity free navigation results.