Single-view Neural Radiance Fields with Depth Teacher
This work addresses the challenge of poor generalization and high data requirements in NeRF for computer vision applications, offering a more efficient solution for single-view rendering.
The paper tackles the problem of novel view synthesis from a single image by developing a NeRF model that combines planar and volume rendering, achieving 5-20% improvements in PSNR and 20-50% error reduction in depth rendering compared to state-of-the-art methods.
Neural Radiance Fields (NeRF) have been proposed for photorealistic novel view rendering. However, it requires many different views of one scene for training. Moreover, it has poor generalizations to new scenes and requires retraining or fine-tuning on each scene. In this paper, we develop a new NeRF model for novel view synthesis using only a single image as input. We propose to combine the (coarse) planar rendering and the (fine) volume rendering to achieve higher rendering quality and better generalizations. We also design a depth teacher net that predicts dense pseudo depth maps to supervise the joint rendering mechanism and boost the learning of consistent 3D geometry. We evaluate our method on three challenging datasets. It outperforms state-of-the-art single-view NeRFs by achieving 5$\sim$20\% improvements in PSNR and reducing 20$\sim$50\% of the errors in the depth rendering. It also shows excellent generalization abilities to unseen data without the need to fine-tune on each new scene.