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

2026-05-12

AI Summary

This work addresses the challenge of retrospective novel view synthesis in synchronized multi-view dynamic scenes, where existing methods often rely on explicit temporal coupling or multi-body constraints. The authors propose a dynamic 3D Gaussian splatting approach that dispenses with explicit temporal consistency constraints. Building upon an initial Structure-from-Motion (SfM) point cloud, the method optimizes Gaussian parameters through temporal propagation to achieve efficient and high-quality novel view synthesis. Furthermore, the study introduces a standardized framework for generating synchronized multi-view dynamic datasets using Blender, along with a reproducible benchmark. Experimental results demonstrate the superiority of the proposed method in terms of both performance and generalization capabilities.

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.

Problem

• novel view synthesis
• dynamic scenes
• 3D Gaussian Splatting
• synchronized multi-view
• benchmark

Innovation

• 3D Gaussian Splatting
• Retrospective Novel View Synthesis
• Synchronized Multi-view
• Dynamic Scene
• Benchmark Framework