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

• URL: http://arxiv.org/abs/2608.13949v1
• Date: Fri, 14 Aug 2026 04:44:14 GMT
• Title: Fast Implicit Neural Light Field Representation via Geometric Decomposition and Multi-Resolution Low-Rank Features
• Abstract summary: Implicit neural representations provide a compact and continuous way to reconstruct dense light fields from sampled ray coordinates.<n>Fast light field reconstruction remains challenging because a light field is a high-dimensional signal with strong spatial-angular redundancy and structured disparity variations.<n>This paper proposes a fast implicit light field representation based on geometric decomposition and multi-resolution low-rank features.
• Score: 5.088590848084556
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• UHD Low-Light Image Enhancement via Real-Time Enhancement Methods with Clifford Information Fusion [51.51707075741303]
  We propose a novel real-time UHD low-light enhancement network based on geometric feature fusion.<n>Our method achieves millisecond-level inference for 4K/8K images on a single consumer-grade device.
  arXiv  Detail & Related papers  (2026-04-10T13:47:04Z)
• PolGS++: Physically-Guided Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction [76.9760302941819]
  PolGS++ is a polarimetric Gaussian Splatting framework for fast reflective surface reconstruction.<n>We introduce a depth-guided visibility mask acquisition mechanism that enables angle-of-polarization (AoP)-based tangent-space consistency constraints.
  arXiv  Detail & Related papers  (2026-03-11T14:11:42Z)
• From Sparse Sensors to Continuous Fields: STRIDE for Spatiotemporal Reconstruction [3.2580743227673694]
  We present STRIDE, a framework that maps high-dimensional spatial fields to a latent state with a temporaltemporal decoder.<n>We show that STRIDE supports super-resolution, supports super-resolution, and remains robust to noise.
  arXiv  Detail & Related papers  (2026-02-04T04:39:23Z)
• Lightweight RGB-D Salient Object Detection from a Speed-Accuracy Tradeoff Perspective [54.91271106816616]
  Current RGB-D methods usually leverage large-scale backbones to improve accuracy but sacrifice efficiency.<n>We propose a Speed-Accuracy Tradeoff Network (SATNet) for Lightweight RGB-D SOD from three fundamental perspectives.<n> Concerning depth quality, we introduce the Depth Anything Model to generate high-quality depth maps.<n>For modality fusion, we propose a Decoupled Attention Module (DAM) to explore the consistency within and between modalities.<n>For feature representation, we develop a Dual Information Representation Module (DIRM) with a bi-directional inverted framework.
  arXiv  Detail & Related papers  (2025-05-07T19:37:20Z)
• ProbeSDF: Light Field Probes for Neural Surface Reconstruction [4.0130618054041385]
  SDF-based differential rendering frameworks have achieved state-of-the-art multiview 3D shape reconstruction.<n>We re-examine this family of approaches by minimally reformulating its core appearance model.<n>We show this performance to be consistently achieved on real data over two widely different and popular application fields.
  arXiv  Detail & Related papers  (2024-12-13T12:18:26Z)
• AniSDF: Fused-Granularity Neural Surfaces with Anisotropic Encoding for High-Fidelity 3D Reconstruction [55.69271635843385]
  We present AniSDF, a novel approach that learns fused-granularity neural surfaces with physics-based encoding for high-fidelity 3D reconstruction.<n>Our method boosts the quality of SDF-based methods by a great scale in both geometry reconstruction and novel-view synthesis.
  arXiv  Detail & Related papers  (2024-10-02T03:10:38Z)
• Iterative approach to reconstructing neural disparity fields from light-field data [7.846043927661275]
  This study proposes a neural disparity field (NDF) that establishes an implicit, continuous representation of scene disparity.<n>NDF enables seamless and precise characterization of disparity variations in three-dimensional scenes.
  arXiv  Detail & Related papers  (2024-07-22T05:06:06Z)
• Phase Guided Light Field for Spatial-Depth High Resolution 3D Imaging [36.208109063579066]
  On 3D imaging, light field cameras typically are of single shot, and they heavily suffer from low spatial resolution and depth accuracy. We propose a phase guided light field algorithm to significantly improve both the spatial and depth resolutions for off-the-shelf light field cameras.
  arXiv  Detail & Related papers  (2023-11-17T15:08:15Z)
• Light Field Reconstruction Using Convolutional Network on EPI and Extended Applications [78.63280020581662]
  A novel convolutional neural network (CNN)-based framework is developed for light field reconstruction from a sparse set of views. We demonstrate the high performance and robustness of the proposed framework compared with state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2021-03-24T08:16:32Z)
• Leveraging Spatial and Photometric Context for Calibrated Non-Lambertian Photometric Stereo [61.6260594326246]
  We introduce an efficient fully-convolutional architecture that can leverage both spatial and photometric context simultaneously. Using separable 4D convolutions and 2D heat-maps reduces the size and makes more efficient.
  arXiv  Detail & Related papers  (2021-03-22T18:06:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.