A Single Atlas is All You Need: Decoder-Side Gaussian Splatting for Immersive Video

TL;DR

This paper introduces DSGS, a decoder-side Gaussian splatting framework for immersive video that reduces bandwidth and improves view synthesis quality by leveraging lossy compression as a low-pass filter.

Contribution

It replaces traditional depth estimation with feed-forward 3D Gaussian splatting inference, enabling efficient, high-quality view synthesis directly on the decoder side from compressed data.

Findings

Lossy compression acts as an implicit low-pass filter stabilizing splat prediction.

DSGS outperforms DSDE with +5.79 dB BD-PSNR and +0.054 BD-SSIM gains.

Reduces inter-view Delta IV-PSNR from 17.2 dB to 6.4 dB.

Abstract

Immersive video delivery is bottlenecked by pixel-rate constraints, making the transmission of high-resolution depth maps or explicit 3D volumetric data expensive. Decoder-Side Depth Estimation (DSDE) shifts depth computation to the client, but struggles with complex geometries, inter-view flickering, and non-Lambertian reflections. Conversely, 3D Gaussian Splatting (3DGS) offers state-of-the-art view synthesis, but transmitting splats (or their projected 2D maps) incurs prohibitive bandwidth costs and is poorly aligned with standard video codecs. We propose Decoder-Side Gaussian Splatting (DSGS), a framework that natively replaces the depth-estimation stage of DSDE with feed-forward 3DGS inference, optimizing volumetric scenes entirely on the decoder side from compressed textures and metadata. A central, counterintuitive finding is that lossy compression acts as an implicit low-pass filter stabilizing feed-forward splat prediction: compressed bitstreams exceed lossless quality while shrinking tenfold. Under extreme view sparsity (one 2D atlas comprising 4 input views), DSGS achieves a +5.79 dB BD-PSNR and +0.054 BD-SSIM gain over the DSDE anchor while reducing maximum inter-view Delta IV-PSNR from 17.2 dB to 6.4 dB, minimizing the domain shift between transmitted and virtual viewports.