In computer vision and computer graphics, 4D reconstruction is the process of capturing the shape and appearance of real objects along a temporal dimension.[1][2][3][4] This process can be accomplished by methods such as depth camera imaging,[1] photometric stereo, or structure from motion,[5] and is also referred to as spatio-temporal reconstruction.[4]
Extending the concept of 3D Gaussian Splatting, the 4D Gaussian Splatting incorporates a time component, allowing for dynamic scene rendering. It represents and renders dynamic scenes, with a focus on modeling complex motions while maintaining efficiency.[6] The method uses a HexPlane to connect different adjacent Gaussians, providing an accurate representation of position and shape deformations. By utilizing only a single set of canonical 3D Gaussians, and predictive analytics, the 4D Gaussian splatting method models how they move over different timestamps.[7]
Achievements of this technique include real-time rendering on dynamic scenes with high resolutions, while maintaining quality. It showcases potential applications for future developments in film and other media, although there are current limitations regarding the length of motion captured.[7]