Log In Sign Up

Deep Surface Light Fields

by   Anpei Chen, et al.

A surface light field represents the radiance of rays originating from any points on the surface in any directions. Traditional approaches require ultra-dense sampling to ensure the rendering quality. In this paper, we present a novel neural network based technique called deep surface light field or DSLF to use only moderate sampling for high fidelity rendering. DSLF automatically fills in the missing data by leveraging different sampling patterns across the vertices and at the same time eliminates redundancies due to the network's prediction capability. For real data, we address the image registration problem as well as conduct texture-aware remeshing for aligning texture edges with vertices to avoid blurring. Comprehensive experiments show that DSLF can further achieve high data compression ratio while facilitating real-time rendering on the GPU.


page 2

page 3

page 6

page 8

page 11

page 12

page 13

page 14


DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Rendering

We introduce DoubleField, a novel representation combining the merits of...

A System for Acquiring, Processing, and Rendering Panoramic Light Field Stills for Virtual Reality

We present a system for acquiring, processing, and rendering panoramic l...

Semantic See-Through Rendering on Light Fields

We present a novel semantic light field (LF) refocusing technique that c...

A Promising Method for Touch-typing Keyboard Rendering

We have developed a novel button click rendering mechanism based on acti...

Image Sampling with Quasicrystals

We investigate the use of quasicrystals in image sampling. Quasicrystals...

Generative Occupancy Fields for 3D Surface-Aware Image Synthesis

The advent of generative radiance fields has significantly promoted the ...