Neural Point Light Fields

TL;DR

Neural Point Light Fields offer an efficient way to synthesize realistic novel views of large scenes by representing scenes with sparse point clouds and learned implicit light fields, overcoming limitations of dense volumetric methods.

Contribution

This work introduces Neural Point Light Fields, a novel approach combining sparse point clouds with implicit light fields for large-scale scene rendering.

Findings

Effective novel view synthesis for large scenes.

Able to generate videos along unseen trajectories.

Outperforms existing implicit methods on large driving scenarios.

Abstract

We introduce Neural Point Light Fields that represent scenes implicitly with a light field living on a sparse point cloud. Combining differentiable volume rendering with learned implicit density representations has made it possible to synthesize photo-realistic images for novel views of small scenes. As neural volumetric rendering methods require dense sampling of the underlying functional scene representation, at hundreds of samples along a ray cast through the volume, they are fundamentally limited to small scenes with the same objects projected to hundreds of training views. Promoting sparse point clouds to neural implicit light fields allows us to represent large scenes effectively with only a single radiance evaluation per ray. These point light fields are a function of the ray direction, and local point feature neighborhood, allowing us to interpolate the light field conditioned training images without dense object coverage and parallax. We assess the proposed method for novel view synthesis on large driving scenarios, where we synthesize realistic unseen views that existing implicit approaches fail to represent. We validate that Neural Point Light Fields make it possible to predict videos along unseen trajectories previously only feasible to generate by explicitly modeling the scene.