Controllable Motion-Blur Effects in Still Images

Abstract

Motion blur in a photo is the consequence of object motion during the image acquisition. It results in a visible trail along the motion of a recorded object and can be used by photographers to convey a sense of motion. Nevertheless, it is very challenging to acquire this effect as intended and requires much experience from the photographer. To achieve actual control over the motion blur, one could be added in a post process but current solutions require complex manual intervention and can lead to artifacts that mix moving and static objects incorrectly. In this paper, we propose a novel method to add motion blur to a single image that generates the illusion of a photographed motion. Relying on a minimal user input, a filtering process is employed to produce a virtual motion effect. It carefully handles object boundaries to avoid artifacts produced by standard filtering methods. We illustrate the effectiveness of our solution with various complex examples, including multi-directional blur, reflections, multiple objects, and illustrate how several motion-related artistic effects can be achieved. Our post-processing solution is an alternative to capturing the intended real-world motion blur directly and enables fine-grained control of the motion-blur effect.

Computational Long Exposure Mobile Photography

“…Unlike other works which realize a long exposure effect [Lancelle et al 2019;Lee et al 2009;Luo et al 2018Luo et al , 2020Mikamo et al 2021;Teramoto et al 2010], our pipeline is a responsive mobile phone capture experience. Therefore, we also compare our results to released capture experiences for consumer phones.…”

“…Determining the subject of a background blur capture is a hard problem. Many synthetic long exposure pipelines avoid it altogether by requiring manually tagging the subject region, or using a heuristic such as the middle region of the image [Lancelle et al 2019;Luo et al 2018;Mikamo et al 2021]. In contrast, we present a pipeline which determines the subject region automatically by predicting visual saliency and face regions.…”

“…There is a large body of prior work on synthesizing motion-blur, in the context of non-photorealistic rendering [Lee et al 2009], stop-motion animation [Brostow and Essa 2001], or 3D computer graphics rendering in real-time [Rønnow et al 2021] or offline [Lehtinen et al 2011;Navarro et al 2011]. There is work describing single photograph post-processing interactive applications to create artistic motion effects [Luo et al 2018[Luo et al , 2020Teramoto et al 2010] or that process multiple previously stabilized images and can achieve non-physical renditions [Salamon et al 2019].…”

A patch-based regression convolutional neural network for motion blur estimation

“…We additionally hope to study other more sophisticated forms of motion bur such as those in Ref. 14. Finally, further study is warranted in the effects of blur estimation in strongly homogeneous regions, such as the flat black background of the images in Ref.…”

ShutterApp: Spatio‐temporal Exposure Control for Videos

“…[OLXK18,CGHD19,LL18]) can segment the masks, the process is still costly and challenging, as motion blur trails will jut out of the masks. Because of this, a singleframe motion blur requires inpainting to fill in the partially visible background underneath the motion trails [LSE19]. Consequently, such spatial mixing is difficult to obtain for real-world footage.…”