CPSL: Representing Volumetric Video via Content-Promoted Scene Layers

TL;DR

CPSL introduces a compact 2.5D video representation that enables scalable, real-time volumetric video synthesis by decomposing frames into content-guided layers, significantly reducing costs while maintaining high perceptual quality.

Contribution

The paper proposes CPSL, a novel 2.5D scene layer method guided by depth and saliency, facilitating efficient, high-quality volumetric video rendering without expensive 3D reconstruction.

Findings

Outperforms layer-based and neural-field methods in perceptual quality.

Reduces storage and rendering costs by several folds.

Supports real-time playback with standard video codecs.

Abstract

Volumetric video enables immersive and interactive visual experiences by supporting free viewpoint exploration and realistic motion parallax. However, existing volumetric representations from explicit point clouds to implicit neural fields, remain costly in capture, computation, and rendering, which limits their scalability for on-demand video and reduces their feasibility for real-time communication. To bridge this gap, we propose Content-Promoted Scene Layers (CPSL), a compact 2.5D video representation that brings the perceptual benefits of volumetric video to conventional 2D content. Guided by per-frame depth and content saliency, CPSL decomposes each frame into a small set of geometry-consistent layers equipped with soft alpha bands and an edge-depth cache that jointly preserve occlusion ordering and boundary continuity. These lightweight, 2D-encodable assets enable parallax-corrected novel-view synthesis via depth-weighted warping and front-to-back alpha compositing, bypassing expensive 3D reconstruction. Temporally, CPSL maintains inter-frame coherence using motion-guided propagation and per-layer encoding, supporting real-time playback with standard video codecs. Across multiple benchmarks, CPSL achieves superior perceptual quality and boundary fidelity compared with layer-based and neural-field baselines while reducing storage and rendering cost by several folds. Our approach offer a practical path from 2D video to scalable 2.5D immersive media.