Adobe, Inc.

Abhishek Shah

Sagar Tandon

Andaleeb Fatima

Sameer Bhatt

Gagan Singhal

Ankit Pangasa

Ram Bhushan Agrawal

Abhinav Darbari

Angad Kumar Gupta

Shailesh Kumar

Anuj Dhawan

Arvinder Singh

Ram Narain Yadav

P B Ramesh

Sharad Baliyan

Puneet Singhal

Mike Iampietro

Sarandeep Singh

Ankuj Gupta

Vibha Tanda

Rotish Kumar

Subbiah Muthuswamy Pillai

Arshla Jindal

Brajesh Kumar

Embodiments of the present invention provide systems, methods, and computer storage media for organization of digital media in which a digital media gallery is organized based on underlying events or occasions by leveraging content tags associated with media. Content tags and their corresponding confidence scores for a set of media are compared with correlation scores of content tags with certain event types. Upon receipt of a set of media, candidate event types may be determined based on content tags associated with the set of media and relevant tags for different event types. The candidate event types are scored based on the confidence scores and the correlations scores for each candidate event type. The highest scoring candidate event type may be presented to the user as the event type for the set of media.

Context-based organization of digital media

A digital medium environment is described to improve moving graphical user interface objects using predictive drop zones that are generated based on user input operations. In one example, a user input processing system receives user input, such as selection and movement of a graphical object. The user input processing system monitors the user input to determine velocity, acceleration, location, and direction of the graphical object as moved by the user input. From the monitoring, the user input processing system continuously determines a location for a predicted drop zone in the user interface that represents an ending point for the movement. The predicted drop zone is then rendered on the user interface in real-time until termination of the input, at which point the user input processing system moves the graphical object to the location of the predicted drop zone, rather than to a pointing device location.

Drop zone prediction for user input operations

Systems and techniques are disclosed for automatically creating a group shot image by intelligently selecting a best frame of a video clip to use as a base frame and then intelligently merging features of other frames into the base frame. In an embodiment, this involves determining emotional alignment scores and eye scores for the individual frames of the video clip. The emotional alignment scores for the frames are determined by assessing the faces in each of the frames with respect to an emotional characteristic (e.g., happy, sad, neutral, etc.). The eye scores for the frames are determined based on assessing the states of the eyes (e.g., fully open, partially open, closed, etc.) of the faces in individual frames. Comprehensive scores for the individual frames are determined based on the emotional alignment scores and the eye scores, and the frame having the best comprehensive score is selected as the base frame.

Automatic creation of a group shot image from a short video clip using intelligent select and merge

Technologies for video-based document scanning are disclosed. The video scanning system may divide a video into segments. A segment has frames with a common feature. For a segment, the video scanning system is configured to rank the frames in the segment, e.g., based on motion characteristics, zoom characteristics, aesthetics characteristics, quality characteristics, etc., of the frames. Accordingly, the system can generate a scan from a selected frame in a segment, e.g., based on the rank of the selected frame in the segment.

Video-based document scanning

Object tracking verification techniques are described as implemented by a computing device. In one example, feature points are selected on and along a boundary of an object to be tracked, e.g., in an initial frame of a digital video, which are referred to as 'feature points.' Tracking of the feature points is verified by the computing device between frames. If the feature points have been found to deviate from the object, the feature points are reselected. To verify the feature points, a number of tracked features points in a subsequent frame is compared to a number of feature points used to initiate tracking with respect to a threshold. Based on this comparison, if a number of feature points is 'lost' in the subsequent frame that is greater than the threshold, the feature points are reselected for tracking the object in subsequent frames of the video.

Object tracking verification in digital video

Certain embodiments involve a model for enhancing text in electronic content. For example, a system obtains electronic content comprising input text and converts the electronic content into a grayscale image. The system also converts the grayscale image into a binary image using a grid-based grayscale-conversion filter, which can include: generating a grid of pixels on the grayscale image; determining a plurality of grid-pixel threshold values at intersection points in the grid of pixels; determining a plurality of estimated pixel threshold values based on the plurality of grid-pixel threshold values; and converting the grayscale image into the binary image using the plurality of grid-pixel threshold values and the plurality of estimated pixel threshold values. The system also generates an interpolated image based on the electronic content and the binary image. The interpolated image includes output text that is darker than the input text. The system can then output the interpolated image.

Text enhancement using a binary image generated with a grid-based grayscale-conversion filter

Techniques for automatic creation of media collages are described. In one or more implementations, unwanted frames are identified and removed from items of media content. A media score is then determined for items of media content based on characteristics of an appearance of the items within a plurality of collage templates. A template score is determined for each collage template of the plurality of collage templates by combining the media scores for each media item of the plurality of media items included in a collage template. At least one of the plurality of collage templates is selected based on determined template scores. Then, at least one media collage is outputted based on the selected collage templates.

Automatic creation of media collages

Computer-implemented systems and methods herein disclose automatic haze correction in a digital video. In one example, a video dehazing module identifies a scene including a set of video frames. The video dehazing module identifies the dark channel, brightness, and atmospheric light characteristics in the scene. For each video frame in the scene, the video dehazing module determines a unique haze correction amount parameter by taking into account the dark channel, brightness, and atmospheric light characteristics. The video dehazing module applies the unique haze correction amount parameters to each video frame and thereby generates a sequence of dehazed video frames.

Systems and techniques for automatic image haze removal across multiple video frames

An automated motion-blur detection process can detect frames in digital videos where only a part of the frame exhibits motion blur. Certain embodiments programmatically identify a plurality of feature points within a video clip, and calculate a speed of each feature point within the video clip. A collective speed of the plurality of feature points is determined based on the speed of each feature point. A selection factor is compared to a selection threshold for each video frame. The selection factor is based at least in part on the collective speed of the plurality of feature points. Based on this comparison, at least one video frame from within the video clip is selected. In some aspects, the selected video frame is relatively free of motion blur, even motion blur that occurs in only a part of the image.

Detection of partially motion-blurred video frames

Systems and methods for segmenting video. A segmentation application executing on a computing device receives a video including video frames. The segmentation application calculates, using a predictive model trained to evaluate quality of video frames, a first aesthetic score for a first video frame and a second aesthetic score for a second video frame. The segmentation application determines that the first aesthetic score and the second aesthetic score differ by a quality threshold and that a number of frames between the first video frame and the second video frame exceeds a duration threshold. The segmentation application creates a video segment by merging a subset of video frames ranging from the first video frame to an segment-end frame preceding the second video frame.

Video segmentation using predictive models trained to provide aesthetic scores

Automatic frame selection and action shot generation techniques in a digital medium environment are described. A computing device identifies an object in a foreground of video data. A determination is then made by the computing device as to motion of the object exhibited between frames of the video data. A subset of frames is then selected by the computing device based on a determined motion of the identified object depicting an action sequence. An action shot is generated by the computing device by overlaying the identified objects in the selected frames on a background.

Automated action shot generation in a digital medium environment

A method for editing nested video sequences includes receiving a selection, by a user in a graphical user interface (GUI), of a video clip that corresponds to a nested video sequence of a parent video sequence. In response to the selection, each higher layer of the parent video sequence than a given layer that comprises the video clip is disabling from being rendered in a monitor view of the GUI. An image of the parent video sequence is rendered in the monitor view while each higher layer is disabled from being rendered. Also while each higher layer is disabled from being rendered, a manipulation by the user of a GUI element that corresponds to a graphical object from the nested video sequence is received. The manipulation is applied to the graphical object from the nested video sequence.

Editing nested video sequences

Systems and methods disclosed herein provide automatic and intelligent video sorting in the context of creating video compositions. A computing device sorts a media bin of videos in the user's work area based on similarity to the videos included in the video composition being created. When a user selects or includes a particular video on the composition's timeline, the video is compared against the entire video collection to change the display of videos in the media bin. In one example, videos that have similar tags to a selected video are prioritized at the top. Only a subset of frames of each of the videos are used to use to identify video tags. Intelligently selecting tags using a subset of frames from each video rather than using all frames enables more efficient and accurate tagging of videos, which facilitates quicker and more accurate comparison of video similarities.

Automatic and intelligent video sorting

Embodiments of the present invention provide systems, methods, and computer storage media directed to operations to facilitate generation of time-lapse videos. In accordance with embodiments described herein, frames of a photographic input are analyzed to detect activity occurring across frame pairs. The photographic input, such as video input, is input for which a time-lapse video is to be generated. Activity detected across frame pairs is used to automatically select a plurality of the frames for use in generating the time-lapse video. At least a portion of the frames selected in accordance with the activity detected across frame pairs is used to generate the time-lapse video.

Growing community of inventors

Delhi, India

Abhishek Shah