DINER: Depth-aware Image-based NEural Radiance fields

TL;DR

DINER introduces a depth-aware neural radiance field method that improves 3D scene reconstruction and novel view synthesis from sparse images by incorporating depth information, resulting in higher quality and larger viewpoint changes.

Contribution

The paper proposes novel techniques to integrate depth into neural radiance fields, enhancing scene reconstruction and view synthesis capabilities.

Findings

Higher synthesis quality than previous methods

Effective processing of views with greater disparity

Improved scene completeness and viewpoint flexibility

Abstract

We present Depth-aware Image-based NEural Radiance fields (DINER). Given a sparse set of RGB input views, we predict depth and feature maps to guide the reconstruction of a volumetric scene representation that allows us to render 3D objects under novel views. Specifically, we propose novel techniques to incorporate depth information into feature fusion and efficient scene sampling. In comparison to the previous state of the art, DINER achieves higher synthesis quality and can process input views with greater disparity. This allows us to capture scenes more completely without changing capturing hardware requirements and ultimately enables larger viewpoint changes during novel view synthesis. We evaluate our method by synthesizing novel views, both for human heads and for general objects, and observe significantly improved qualitative results and increased perceptual metrics compared to the previous state of the art. The code is publicly available for research purposes.