GeoNeRF: Generalizing NeRF with Geometry Priors

TL;DR

GeoNeRF introduces a novel neural radiance field approach that leverages geometry priors and attention mechanisms for photorealistic view synthesis, outperforming existing models with efficient computation and adaptability to RGBD data.

Contribution

It presents GeoNeRF, a generalizable neural rendering framework combining a geometry reasoner and transformer-based renderer, enabling high-quality view synthesis with efficient fine-tuning and depth integration.

Findings

Outperforms state-of-the-art models on synthetic and real datasets.

Achieves competitive results with less computational cost.

Adapts to RGBD images using a modified geometry reasoner.

Abstract

We present GeoNeRF, a generalizable photorealistic novel view synthesis method based on neural radiance fields. Our approach consists of two main stages: a geometry reasoner and a renderer. To render a novel view, the geometry reasoner first constructs cascaded cost volumes for each nearby source view. Then, using a Transformer-based attention mechanism and the cascaded cost volumes, the renderer infers geometry and appearance, and renders detailed images via classical volume rendering techniques. This architecture, in particular, allows sophisticated occlusion reasoning, gathering information from consistent source views. Moreover, our method can easily be fine-tuned on a single scene, and renders competitive results with per-scene optimized neural rendering methods with a fraction of computational cost. Experiments show that GeoNeRF outperforms state-of-the-art generalizable neural rendering models on various synthetic and real datasets. Lastly, with a slight modification to the geometry reasoner, we also propose an alternative model that adapts to RGBD images. This model directly exploits the depth information often available thanks to depth sensors. The implementation code is available at https://www.idiap.ch/paper/geonerf.