arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.04013cs.CVcs.ITcs.MMmath.IT
收藏

3D-LMVIC:基于3D高斯几何先验的学习型多视图图像编码

3D-LMVIC: Learning-based Multi-View Image Coding with 3D Gaussian Geometric Priors

Yujun Huang, Bin Chen, Niu Lian, Baoyi An, Shu-Tao Xia

AI总结:

针对宽基线多相机系统的复杂视差问题,提出3D-LMVIC框架,利用3D Gaussian Splatting几何先验、深度图压缩和视图排序提升压缩与视差估计性能。

摘要:

现有的多视图图像压缩方法通常依赖视图间基于2D投影的相似性来估计视差。虽然这些方法对视差较小的情形(如立体图像中的视差)有效,但在宽基线多相机系统中遇到的更复杂视差面前表现不佳;这类系统常见于虚拟现实和自动驾驶应用。为解决这一局限,本文提出3D-LMVIC,这是一种新颖的基于学习的多视图图像压缩框架,利用3D Gaussian Splatting获取几何先验,以实现准确的视差估计。此外,本文提出一种深度图压缩模型,以最小化视图间的几何冗余;同时提出一种基于所定义视图间距离度量的多视图序列排序策略,以增强相邻视图之间的相关性。实验结果表明,与传统方法和基于学习的方法相比,3D-LMVIC均取得了更优性能。此外,相较于现有双视图方法,它显著提高了视差估计精度。

英文摘要:

Existing multi-view image compression methods often rely on 2D projection-based similarities between views to estimate disparities. While effective for small disparities, such as those in stereo images, these methods struggle with the more complex disparities encountered in wide-baseline multi-camera systems, commonly found in virtual reality and autonomous driving applications. To address this limitation, we propose 3D-LMVIC, a novel learning-based multi-view image compression framework that leverages 3D Gaussian Splatting to derive geometric priors for accurate disparity estimation. Furthermore, we introduce a depth map compression model to minimize geometric redundancy across views, along with a multi-view sequence ordering strategy based on a defined distance measure between views to enhance correlations between adjacent views. Experimental results demonstrate that 3D-LMVIC achieves superior performance compared to both traditional and learning-based methods. Additionally, it significantly improves disparity estimation accuracy over existing two-view approaches.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑