3D Gaussian Splatting for Efficient Retrospective Dynamic Scene Novel View Synthesis with a Standardized Benchmark

TL;DR

This paper demonstrates that in synchronized multi-view settings, 3D Gaussian Splatting can efficiently perform retrospective dynamic scene novel view synthesis without complex temporal constraints, supported by a new benchmark framework.

Contribution

Proposes a simplified approach for dynamic scene NVS in synchronized multi-view setups, removing the need for temporal coupling, and introduces a reproducible dataset framework for benchmarking.

Findings

Efficient retrospective NVS achieved without temporal deformation constraints.

A new Blender-based dataset framework enables reproducible dynamic scene benchmarking.

Demonstrates competitive results of 3DGS in synchronized multi-view scenarios.

Abstract

Retrospective novel view synthesis (NVS) of dynamic scenes is fundamental to applications such as sports. Recent dynamic 3D Gaussian Splatting (3DGS) approaches introduce temporally coupled formulations to enforce motion coherence across time. In this paper, we argue that, in a synchronized multi-view (MV) setting typical of sports, the dynamic scene at each time step is already strongly geometrically constrained. We posit that the availability of calibrated, synchronized viewpoints provides sufficient spatial consistency, and therefore, explicit temporal coupling, or complex multi-body constraints seems unnecessary for retrospective NVS. To this end, we propose an approach tailored for synchronized MV dynamic scene. By initializing the SfM-derived point cloud at the start time and propagating optimized Gaussians over time, we show that efficient retrospective NVS can be achieved without imposing a temporal deformation constraint. Complementing our methodological contribution, we introduce a Dynamic MV dataset framework built on Blender for reproducible NeRF and 3DGS research. The framework generates high-quality, synchronized camera rigs and exports training-ready datasets in standard formats, eliminating inconsistencies in coordinate conventions and data pipelines. Using the framework, we construct a dynamic benchmark suite and evaluate representative NeRF and 3DGS approaches under controlled conditions. Together, we show that, under a synchronized MV setup, efficient retrospective dynamic scene NVS can be achieved using 3DGS. At the same time, the dataset-generation framework enables reproducible and principled benchmarking of dynamic NVS methods.