paper-with-me

Papers

SADN: Learned Light Field Image Compression with Spatial-Angular Decorrelation

2022-02-22 · Kedeng Tong, Xin Jin, Chen Wang, Fan Jiang

Light field image becomes one of the most promising media types for immersive video applications. In this paper, we propose a novel end-to-end spatial-angular-decorrelated network (SADN) for high-efficiency light field image compression. Different from the existing methods that exploit either spatial or angular consistency in the light field image, SADN decouples the angular and spatial information by dilation convolution and stride convolution in spatial-angular interaction, and performs feature fusion to compress spatial and angular information jointly. To train a stable and robust algorithm, a large-scale dataset consisting of 7549 light field images is proposed and built. The proposed method provides 2.137 times and 2.849 times higher compression efficiency relative to H.266/VVC and H.265/HEVC inter coding, respectively. It also outperforms the end-to-end image compression networks by an average of 79.6% bitrate saving with much higher subjective quality and light field consistency.

📄 PDF Abstract BibTeX arXiv:2202.10837

Code (2)

VincentChandelier/SADN 공식 구현 pytorch
VincentChandelier/SADN-QVRF pytorch

Tasks

Image Compression

Methods 이 논문이 사용한 방법론

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Learning Kernel-Modulated Neural Representation for Efficient Light Field Compression

2023-07-12 · Jinglei Shi, Yihong Xu, Christine Guillemot

Light field is a type of image data that captures the 3D scene information by recording light rays emitted from a scene at various orientations. It offers a more immersive perception than classic 2D images but at the cos…

DescriptiveQuantizationTensor Decomposition

Distilled Low Rank Neural Radiance Field with Quantization for Light Field Compression

2022-07-30 · Jinglei Shi, Christine Guillemot

We propose in this paper a Quantized Distilled Low-Rank Neural Radiance Field (QDLR-NeRF) representation for the task of light field compression. While existing compression methods encode the set of light field sub-apert…

NeRFQuantization

Deep Decoding of $\ell_\infty$-coded Light Field Images

2022-01-24 · Muhammad Umair Mukati, Xi Zhang, Xiaolin Wu, Søren Forchhammer

To enrich the functionalities of traditional cameras, light field cameras record both the intensity and direction of light rays, so that images can be rendered with user-defined camera parameters via computations. The ad…

DecoderImage Compression

Sparse Point Clouds Assisted Learned Image Compression

2024-12-20 · Yiheng Jiang, Haotian Zhang, Li Li, Dong Liu 외

In the field of autonomous driving, a variety of sensor data types exist, each representing different modalities of the same scene. Therefore, it is feasible to utilize data from other sensors to facilitate image compres…

Autonomous DrivingImage Compression

SANR: Scene-Aware Neural Representation for Light Field Image Compression with Rate-Distortion Optimization

2025-10-17 · Gai Zhang, Xinfeng Zhang, Lv Tang, Hongyu An 외 arxiv

Light field images capture multi-view scene information and play a crucial role in 3D scene reconstruction. However, their high-dimensional nature results in enormous data volumes, posing a significant challenge for effi…

Image Compression