Seeing What Matters: Perceptual Wrapper with Common Randomness for 3D Gaussian Splatting

2026-06-10

AI Summary

This work addresses the loss of high-frequency details in 3D Gaussian Splatting (3DGS) under memory constraints or rate-distortion optimization, which often results in blurry renderings. To mitigate this issue, the authors propose a plug-and-play, 2D-aware enhancement module that injects pseudorandom Gaussian noise via a lightweight conditional synthesis network. Instead of conventional pixel-level reconstruction losses, the method employs a Wasserstein distance–based feature statistical matching mechanism to enable view- and content-adaptive perceptual quality improvement. Notably, the approach requires no modification to the original 3DGS architecture and is compatible with various existing variants. It achieves superior performance over current methods both subjectively in visual fidelity and objectively in quantitative metrics, while significantly reducing model or file size.

Abstract

While 3D Gaussian Splatting (3DGS) achieves impressive real-time rendering, it frequently struggles to synthesize high-frequency textures, a limitation heavily exacerbated in memory-constrained and rate-distortion-optimized (RDO) pipelines. To address this, we propose a versatile 2D perceptual wrapper that enhances the rendered outputs of existing 3DGS representations in a content- and view-dependent manner. Our method leverages a lightweight synthesis network conditioned on pseudo-random Gaussian noise to synthesize perceptually plausible textures. Supervised by Wasserstein Distortion, the network learns to match local feature statistics rather than strictly enforcing pixel-wise reconstruction fidelity, effectively mitigating the blurriness inherent in standard frameworks. We demonstrate the broad applicability of our plug-and-play approach across vanilla, memory-constrained, and RDO 3DGS methods. Comprehensive subjective and objective experiments confirm that our method significantly improves over existing baselines, yielding superior perceptual quality at sharply reduced file or model sizes.

Problem

• 3D Gaussian Splatting
• high-frequency textures
• rate-distortion optimization
• perceptual quality
• memory-constrained rendering

Innovation

• Perceptual Wrapper
• 3D Gaussian Splatting
• Wasserstein Distortion
• Common Randomness
• Rate-Distortion Optimization