GeCoNeRF: Few-shot Neural Radiance Fields via Geometric Consistency
This work addresses the challenge of 3D scene reconstruction from limited views for applications in computer vision and graphics, representing an incremental improvement over existing methods.
The paper tackles the problem of learning Neural Radiance Fields (NeRF) with few input images by introducing a geometry-aware consistency regularization method, achieving competitive results compared to state-of-the-art few-shot NeRF models.
We present a novel framework to regularize Neural Radiance Field (NeRF) in a few-shot setting with a geometry-aware consistency regularization. The proposed approach leverages a rendered depth map at unobserved viewpoint to warp sparse input images to the unobserved viewpoint and impose them as pseudo ground truths to facilitate learning of NeRF. By encouraging such geometry-aware consistency at a feature-level instead of using pixel-level reconstruction loss, we regularize the NeRF at semantic and structural levels while allowing for modeling view dependent radiance to account for color variations across viewpoints. We also propose an effective method to filter out erroneous warped solutions, along with training strategies to stabilize training during optimization. We show that our model achieves competitive results compared to state-of-the-art few-shot NeRF models. Project page is available at https://ku-cvlab.github.io/GeCoNeRF/.