Method, storage medium and system for generating video based on scene reconstruction

The invention discloses a method, a storage medium and a system for generating a video based on scene reconstruction. The method comprises the following steps: acquiring to-be-reconstructed image data, the to-be-reconstructed image data being used for recording an image of a to-be-reconstructed preset three-dimensional scene; performing sparse reconstruction on the to-be-reconstructed image data to obtain a reconstruction result; implicit modeling is carried out based on the to-be-reconstructed image data and the reconstruction result, and a modeling result is obtained; and generating a target video by using the modeling result, the target video being used for performing scene roaming on a preset three-dimensional scene. The technical problems of many modeling result defects and poor sense of reality of a scene roaming video caused by the fact that scene reconstruction is carried out by adopting a display modeling mode in the prior art are solved. 本申请公开了一种基于场景重建生成视频的方法、存储介质和系统。其中，该方法包括：获取待重建图像数据，其中，待重建图像数据用于记