GCC: A 3DGS Inference Architecture with Gaussian-Wise and Cross-Stage Conditional Processing

TL;DR

GCC is a novel 3D Gaussian Splatting inference accelerator that improves efficiency by dynamically skipping unnecessary preprocessing and reducing redundant Gaussian loading, leading to faster and more energy-efficient rendering.

Contribution

We introduce GCC, a new accelerator with cross-stage conditional processing and Gaussian-wise rendering, addressing inefficiencies in existing 3DGS accelerators.

Findings

GCC achieves higher performance than GSCore.

GCC significantly reduces energy consumption.

GCC effectively minimizes redundant Gaussian processing.

Abstract

3D Gaussian Splatting (3DGS) has emerged as a leading neural rendering technique for high-fidelity view synthesis, prompting the development of dedicated 3DGS accelerators for resource-constrained platforms. The conventional decoupled preprocessing-rendering dataflow in existing accelerators has two major limitations: 1) a significant portion of preprocessed Gaussians are not used in rendering, and 2) the same Gaussian gets repeatedly loaded across different tile renderings, resulting in substantial computational and data movement overhead. To address these issues, we propose GCC, a novel accelerator designed for fast and energy-efficient 3DGS inference. GCC introduces a novel dataflow featuring: 1) \textit{cross-stage conditional processing}, which interleaves preprocessing and rendering to dynamically skip unnecessary Gaussian preprocessing; and 2) \textit{Gaussian-wise rendering}, ensuring that all rendering operations for a given Gaussian are completed before moving to the next, thereby eliminating duplicated Gaussian loading. We also propose an alpha-based boundary identification method to derive compact and accurate Gaussian regions, thereby reducing rendering costs. We implement our GCC accelerator in 28nm technology. Extensive experiments demonstrate that GCC significantly outperforms the state-of-the-art 3DGS inference accelerator, GSCore, in both performance and energy efficiency.