Using interpolation to generate a video from static images

A computing device comprising:

• one or more processors;
• and
• a memory coupled to the one or more processors, with instructions stored thereon that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
• selecting, from a collection of images associated with a user account, candidate pairs of images, wherein each pair includes a first static image and a second static image from the user account;
• applying a filter to select a particular pair of images from the candidate pairs of images, wherein the filter includes a time filter that excludes the one or more of the candidate pairs of images when a time difference between respective timestamps associated with the first static image of the pair and the second static image of the pair is greater than a time threshold;
• generating, using an image interpolator, one or more intermediate images based on the particular pair of images;
• and
• generating a video that includes three or more frames arranged in a sequence, wherein a first frame of the sequence is the first static image, a last frame of the sequence is the second static image, and each of the one or more intermediate images is a corresponding intermediate frame of the sequence between the first frame and the last frame.

A non-transitory computer-readable medium with instructions stored thereon that, when executed by one or more computers, cause the one or more computers to perform operations, the operations comprising:

• selecting, from a collection of images associated with a user account, candidate pairs of images, wherein each pair includes a first static image and a second static image from the user account;
• applying a filter to select a particular pair of images from the candidate pairs of images, wherein the filter includes a time filter that excludes the one or more of the candidate pairs of images when a time difference between respective timestamps associated with the first static image of the pair and the second static image of the pair is greater than a time threshold;
• generating, using an image interpolator, one or more intermediate images based on the particular pair of images;
• and
• generating a video that includes three or more frames arranged in a sequence, wherein a first frame of the sequence is the first static image, a last frame of the sequence is the second static image, and each of the one or more intermediate images is a corresponding intermediate frame of the sequence between the first frame and the last frame.

A computer-implemented method comprising:

• selecting, from a collection of images associated with a user account, candidate pairs of images, wherein each pair includes a first static image and a second static image from the user account;
• applying a filter to select a particular pair of images from the candidate pairs of images, wherein the filter includes a motion filter that excludes one or more of the candidate pairs of images by:
• estimating motion between the first static image and the second static image of the candidate pair;
• and
• determining that the motion between the first static image and the second static image of the candidate pair is less than a minimum motion threshold;
• generating, using an image interpolator, one or more intermediate images based on the particular pair of images;
• and
• generating a video that includes three or more frames arranged in a sequence, wherein a first frame of the sequence is the first static image, a last frame of the sequence is the second static image, and each of the one or more intermediate images is a corresponding intermediate frame of the sequence between the first frame and the last frame.

A computer-implemented method comprising:

• selecting, from a collection of images associated with a user account, candidate pairs of images, wherein each pair includes a first static image and a second static image from the user account;
• applying a filter to select a particular pair of images from the candidate pairs of images, wherein the filter includes a filter machine-learning model that excludes the one or more of the candidate pairs of images by:
• generating feature vectors that represent the first static image and the second static image in each of the candidate pairs;
• and
• excluding the one or more of the candidate pairs that correspond to respective feature vectors where a distance between the respective feature vectors is greater than a threshold vector distance, wherein the feature vectors are mathematical representations and wherein mathematical representations of similar images are closer in vector space than the mathematical representations of dissimilar images;
• generating, using an image interpolator, one or more intermediate images based on the particular pair of images;
• and
• generating a video that includes three or more frames arranged in a sequence, wherein a first frame of the sequence is the first static image, a last frame of the sequence is the second static image, and each of the one or more intermediate images is a corresponding intermediate frame of the sequence between the first frame and the last frame.

A computer-implemented method comprising:

• selecting, from a collection of images associated with a user account, candidate pairs of images, wherein each pair includes a first static image and a second static image from the user account;
• applying a filter to select a particular pair of images from the candidate pairs of images;
• generating, using an image interpolator, one or more intermediate images based on the particular pair of images;
• determining that a frame interpolation failure occurs if the filter excludes the one or more intermediate images;
• responsive to the frame interpolation failure occurring, generating additional one or more intermediate images;
• and
• generating a video that includes three or more frames arranged in a sequence, wherein a first frame of the sequence is the first static image, a last frame of the sequence is the second static image, and each of the one or more intermediate images is a corresponding intermediate frame of the sequence between the first frame and the last frame.

A computer-implemented method comprising:

• selecting, from a collection of images associated with a user account, candidate pairs of images, wherein each pair includes a first static image and a second static image from the user account;
• applying a filter to select a particular pair of images from the candidate pairs of images;
• generating, using an image interpolator, one or more intermediate images based on the particular pair of images;
• and
• generating a video that includes three or more frames arranged in a sequence, wherein a first frame of the sequence is the first static image, a last frame of the sequence is the second static image, and each of the one or more intermediate images is a corresponding intermediate frame of the sequence between the first frame and the last frame;
• and
• wherein generating the video includes, generating, using a depth machine-learning model, a three-dimensional representation of a scene in the first static image based on a prediction of depth of the first static image, wherein the depth machine-learning model is a classifier that receives the first static image as input, wherein the video includes a camera effect that is generated based on the three-dimensional representation of the scene.