Single-Image Deblurring, Trajectory and Shape Recovery of Fast Moving Objects With Denoising Diffusion Probabilistic Models

Radim Spetlik, Denys Rozumnyi, Jiří Matas; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, pp. 6857-6866

Blurry appearance of fast moving objects in video frames was successfully used to reconstruct the object appearance and motion in both 2D and 3D domains. The proposed method addresses the novel, severely ill-posed, task of single-image fast moving object deblurring, shape, and trajectory recovery -- previous approaches require at least three consecutive video frames. Given a single image, the method outputs the object 2D appearance and position in a series of sub-frames as if captured by a high-speed camera (i.e. temporal super-resolution). The proposed SI-DDPM-FMO method is trained end-to-end on a synthetic dataset with various moving objects, yet it generalizes well to real-world data from several publicly available datasets. SI-DDPM-FMO performs similarly to or better than recent multi-frame methods and a carefully designed baseline method.