P-GSVC: Layered Progressive 2D Gaussian Splatting for Scalable Image and Video

2026-03-11

AI Summary

Existing approaches lack a unified and scalable Gaussian representation capable of simultaneously supporting progressive quality and resolution reconstruction for both images and videos. This work proposes a hierarchical progressive 2D Gaussian splatting framework that enables coarse-to-fine scalable reconstruction through a base layer and multiple enhancement layers. A cross-layer joint training mechanism is introduced to concurrently optimize Gaussian parameters across all layers, ensuring inter-layer compatibility and reconstruction stability. To the best of our knowledge, this is the first method to achieve a unified hierarchical Gaussian representation for both images and videos. It significantly outperforms sequential layer-by-layer training strategies, yielding PSNR improvements of 2.6 dB for images and 1.9 dB for videos.

Technology Category

• Computer Vision: Representation Learning for Vision
• Machine Learning: Representation Learning
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Gaussian splatting has emerged as a competitive explicit representation for image and video reconstruction. In this work, we present P-GSVC, the first layered progressive 2D Gaussian splatting framework that provides a unified solution for scalable Gaussian representation in both images and videos. P-GSVC organizes 2D Gaussian splats into a base layer and successive enhancement layers, enabling coarse-to-fine reconstructions. To effectively optimize this layered representation, we propose a joint training strategy that simultaneously updates Gaussians across layers, aligning their optimization trajectories to ensure inter-layer compatibility and a stable progressive reconstruction. P-GSVC supports scalability in terms of both quality and resolution. Our experiments show that the joint training strategy can gain up to 1.9 dB improvement in PSNR for video and 2.6 dB improvement in PSNR for image when compared to methods that perform sequential layer-wise training. Project page: https://longanwang-cs.github.io/PGSVC-webpage/

Problem

• Gaussian splatting
• scalable representation
• progressive reconstruction
• layered representation
• image and video reconstruction

Innovation

• Progressive Gaussian Splatting
• Layered Representation
• Joint Training
• Scalable Reconstruction
• 2D Gaussian Splatting