{"slug": "fast-implicit-neural-light-field-representation-via-geometric-decomposition-and", "title": "Fast Implicit Neural Light Field Representation via Geometric Decomposition and Multi-Resolution Low-Rank Features", "summary": "Researchers propose a fast implicit neural light field representation that decomposes a 4D light field into horizontal disparity, spatial texture, and vertical disparity planes, each represented by multi-resolution low-rank features. The method, detailed in arXiv:2608.13949v1, achieves competitive reconstruction quality on public datasets while offering a better trade-off among model parameters, training time, and inference efficiency.", "body_md": "arXiv:2608.13949v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/fast-implicit-neural-light-field-representation-via-geometric-decomposition-and", "canonical_source": "https://arxiv.org/abs/2608.13949", "published_at": "2026-08-17 04:00:00+00:00", "updated_at": "2026-08-17 04:12:02.960107+00:00", "lang": "en", "topics": ["machine-learning", "computer-vision"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/fast-implicit-neural-light-field-representation-via-geometric-decomposition-and", "markdown": "https://wpnews.pro/news/fast-implicit-neural-light-field-representation-via-geometric-decomposition-and.md", "text": "https://wpnews.pro/news/fast-implicit-neural-light-field-representation-via-geometric-decomposition-and.txt", "jsonld": "https://wpnews.pro/news/fast-implicit-neural-light-field-representation-via-geometric-decomposition-and.jsonld"}}