Controlling Motion Blur in Synthetic Long Time Exposures

Abstract

In a photo, motion blur can be used as an artistic style to convey motion and to direct attention. In panning or tracking shots, a moving object of interest is followed by the camera during a relatively long exposure. The goal is to get a blurred background while keeping the object sharp. Unfortunately, it can be difficult to impossible to precisely follow the object. Often, many attempts or specialized physical setups are needed. This paper presents a novel approach to create such images. For capturing, the user is only required to take a casually recorded hand‐held video that roughly follows the object. Our algorithm then produces a single image which simulates a stabilized long time exposure. This is achieved by first warping all frames such that the object of interest is aligned to a reference frame. Then, optical flow based frame interpolation is used to reduce ghosting artifacts from temporal undersampling. Finally, the frames are averaged to create the result. As our method avoids segmentation and requires little to no user interaction, even challenging sequences can be processed successfully. In addition, artistic control is available in a number of ways. The effect can also be applied to create videos with an exaggerated motion blur. Results are compared with previous methods and ground truth simulations. The effectiveness of our method is demonstrated by applying it to hundreds of datasets. The most interesting results are shown in the paper and in the supplemental material.

A Method for Adding Motion-Blur on Arbitrary Objects by Using Auto-Segmentation and Color Compensation Techniques

“…In addition, our method can emphasize the dynamism of the target object by changing the size of the motion blur for the artistic purpose (Figure 5(b)). We compare our result with the existing method [25] in Fig. 6.…”

“…The technique requires special high fps cameras and is only applicable to mostly static scenes. The other approach is to capture sharp images and add blur to the background afterward using multiple images [6,7,8,9,10] or video [11]. These techniques are based on object tracking to extract foreground objects and add blur to background.…”

ShutterApp: Spatio‐temporal Exposure Control for Videos

“…Postprocessed motion blur simulates a long exposure shutter by accumulating video frames. Such frame aggregation has been explored by tracking image features to backproject the motion onto a single background image [LWCT14] or by stabilizing the video on the focus object and averaging the moving pixels [LDG19]. In both cases, the blur effect is created from camera motion.…”

“…Other approaches use optical flow and/or 3D motion vectors to globally track and create a per-pixel motion blur [RSM]. Spatially-varying blur requires masking and layer compositing via external software [RSM] or soft brushes [LDG19]. Nonetheless, the temporal motion blur strength is constant after each keyframe.…”

Makna multikultural photomotion motion [e] motion karya Andang Iskandar

“…Teknik ini secara prinsip menggunakan foto-foto atau frame by frame foto untuk menghasilkan gambar diam, sekaligus film yang dibuat oleh gabungan foto-foto yang saling berhubungan satu dengan lainnya (Rustiyanti and Listiani, 2017). Teknik ini salah satunya dikenalkan oleh Andang Iskandar yang dikenal sebagai drafter dan pencipta karya fotografi "Photomotion Motion (e) Motion" (Lancelle, Dogan, and Gross 2019;Pagliarulo et al 2019…”