SCIGaussian-D: Dynamic Scene Reconstruction from a Single Snapshot Compressive Image

Yunhao Li, Yuze Yang, Yanan Hu, Xiaoyue Li, Yong Tang, Xin Yuan, Peidong Liu

Keywords: 3D Vision, Computational Imaging, Computational Photography

TL;DR: We introduce SCIGaussian-D, a framework for dynamic 3D scene reconstruction from a single snapshot compressed image using 3D Gaussians with learnable deformations.

Abstract: In this paper, we explore the potential of snapshot compressive imaging (SCI) for dynamic 3D scene reconstruction from a single temporal compressed image. SCI is a low-cost imaging technique that captures high-dimensional information-such as temporal data—using 2D sensors and coded masks, significantly reducing data bandwidth while offering inherent privacy advantages. While recent advances in Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have enabled 3D reconstruction from SCI measurements, these methods are fundamentally limited to static scenes and fail to generalize to dynamic content. To address this, we propose SCIGaussian-D, a novel framework that enables dynamic 3D reconstruction from a single SCI image. Our method represents the scene with 3D Gaussians defined in a canonical space and models motion using learnable deformation fields. By incorporating the SCI imaging model into the training loop, SCIGaussian-D directly reconstructs the dynamic 3D scene and recovers the corresponding camera motion from a single SCI. We evaluate our method on both synthetic and real SCI datasets, demonstrating significant improvements in reconstruction quality over existing baselines. Our results establish a new state of the art for dynamic scene reconstruction within the SCI framework, paving the way for practical applications in high-speed imaging and real-time scene rendering.

Submission Number: 273