Constrained Dynamic Gaussian Splatting

TL;DR

This paper introduces Constrained Dynamic Gaussian Splatting (CDGS), a novel method for 4D scene reconstruction that enforces strict Gaussian budgets during training, optimizing quality and compression for edge devices.

Contribution

The work formulates scene reconstruction as a budget-constrained optimization with a differentiable controller and adaptive capacity allocation, improving efficiency and quality under hardware constraints.

Findings

Achieves over 3x compression compared to state-of-the-art methods.

Maintains error below 2% while adhering to Gaussian budgets.

Enhances rate-distortion performance with a hybrid compression scheme.

Abstract

While Dynamic Gaussian Splatting enables high-fidelity 4D reconstruction, its deployment is severely hindered by a fundamental dilemma: unconstrained densification leads to excessive memory consumption incompatible with edge devices, whereas heuristic pruning fails to achieve optimal rendering quality under preset Gaussian budgets. In this work, we propose Constrained Dynamic Gaussian Splatting (CDGS), a novel framework that formulates dynamic scene reconstruction as a budget-constrained optimization problem to enforce a strict, user-defined Gaussian budget during training. Our key insight is to introduce a differentiable budget controller as the core optimization driver. Guided by a multi-modal unified importance score, this controller fuses geometric, motion, and perceptual cues for precise capacity regulation. To maximize the utility of this fixed budget, we further decouple the optimization of static and dynamic elements, employing an adaptive allocation mechanism that dynamically distributes capacity based on motion complexity. Furthermore, we implement a three-phase training strategy to seamlessly integrate these constraints, ensuring precise adherence to the target count. Coupled with a dual-mode hybrid compression scheme, CDGS not only strictly adheres to hardware constraints (error < 2%}) but also pushes the Pareto frontier of rate-distortion performance. Extensive experiments demonstrate that CDGS delivers optimal rendering quality under varying capacity limits, achieving over 3x compression compared to state-of-the-art methods.