Fast Implicit Neural Light Field Representation via Geometric Decomposition and Multi-Resolution Low-Rank Features

2026-08-14

AI Summary

This study addresses the optimization inefficiency caused by high-dimensional signal redundancy in implicit neural light field reconstruction. We propose a fast representation method based on geometric decomposition and multi-resolution low-rank features. By decoupling the 4D light field into disparity and texture planes, combined with line feature products and lightweight MLP decoding, this approach effectively eliminates spatial-angular redundancy. Experiments on public datasets demonstrate that the proposed method achieves competitive reconstruction quality while establishing a superior balance among model parameters, training speed, and inference efficiency. Consequently, this work significantly enhances the overall performance of implicit light field representations, offering a practical solution to the computational bottlenecks inherent in high-dimensional neural rendering.

Abstract

Implicit neural representations provide a compact and continuous way to reconstruct dense light fields from sampled ray coordinates. However, fast light field reconstruction remains challenging because a light field is a high-dimensional signal with strong spatial-angular redundancy and structured disparity variations. Directly fitting 4D ray coordinates with a neural network often requires considerable optimization time to recover both view appearance and cross-view consistency. To address this issue, this paper proposes a fast implicit light field representation based on geometric decomposition and multi-resolution low-rank features. The proposed method decomposes a 4D light field into a horizontal disparity plane, a spatial texture plane, and a vertical disparity plane. Each plane is represented by a low-rank structure that combines a low-resolution 2D grid with the element-wise product of two high-resolution 1D line features at multiple resolution levels. The fused features are decoded by a lightweight multilayer perceptron to predict RGB values. Experiments on public light field datasets show that the proposed method achieves competitive reconstruction quality while providing a better trade-off among model parameters, training time, and inference efficiency.

Problem

• Implicit Neural Representation
• Light Field Reconstruction
• High-dimensional Signal
• Optimization Efficiency

Innovation

• Geometric Decomposition
• Multi-Resolution Low-Rank Features
• Implicit Neural Representation
• Light Field Reconstruction
• Efficient Representation