# DeFMO: Deblurring and Shape Recovery of Fast Moving Objects Source: [DeFMO: Deblurring and Shape Recovery of Fast Moving Objects]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:23:31.156Z Authors: Denys Rozumnyi, Martin R. Oswald, Vittorio Ferrari, Jiri Matas, Marc Pollefeys Published: 2020-12-01T16:02:04.000Z ## Abstract Objects moving at high speed appear significantly blurred when captured with cameras. The blurry appearance is especially ambiguous when the object has complex shape or texture. In such cases, classical methods, or even humans, are unable to recover the object's appearance and motion. We propose a method that, given a single image with its estimated background, outputs the object's appearance and position in a series of sub-frames as if captured by a high-speed camera (i.e. temporal super-resolution). The proposed generative model embeds an image of the blurred object into a latent space representation, disentangles the background, and renders the sharp appearance. Inspired by the image formation model, we design novel self-supervised loss function terms that boost performance and show good generalization capabilities. The proposed DeFMO method is trained on a complex synthetic dataset, yet it performs well on real-world data from several datasets. DeFMO outperforms the state of the art and generates high-quality temporal super-resolution frames. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Fast Moving Object Deblurring and Trajectory Estimation on Falling Objects v1 (test)](): Fast Moving Object Deblurring and Trajectory Estimation; Falling Objects v1 (test); PSNR: 26.83. - [Fast Moving Object Deblurring and Trajectory Estimation on TbD-3D v1 (test)](): Fast Moving Object Deblurring and Trajectory Estimation; TbD-3D v1 (test); PSNR: 26.23. - [Fast Moving Object Deblurring and Trajectory Estimation on TbD v1 (test)](): Fast Moving Object Deblurring and Trajectory Estimation; TbD v1 (test); PSNR: 25.57. - [Fast moving object deblurring on Falling Objects](): Fast moving object deblurring; Falling Objects; PSNR: 26.83. - [Fast moving object deblurring on TbD-3D Dataset](): Fast moving object deblurring; TbD-3D Dataset; PSNR: 26.23. - [Fast moving object deblurring on TbD Dataset](): Fast moving object deblurring; TbD Dataset; PSNR: 25.57. ## Original sources and implementation [Original paper]() [PDF]() [Implementation]()