Other

Adobe, Inc.

Czech Technical University in Prague

Daniel Sýkora

Elya Shechtman

Jingwan Lu

Paul John Asente

Jakub Fiser

Ondrej Jamriska

Michal Lukác

David P Simons

Michal Lukac

Zhaowen Wang

Vladimir Kim

Wilmot Li

Marek Dvoroznák

David Futschik

Embodiments are disclosed for translating an image from a source visual domain to a target visual domain. In particular, in one or more embodiments, the disclosed systems and methods comprise a training process that includes receiving a training input including a pair of keyframes and an unpaired image. The pair of keyframes represent a visual translation from a first version of an image in a source visual domain to a second version of the image in a target visual domain. The one or more embodiments further include sending the pair of keyframes and the unpaired image to an image translation network to generate a first training image and a second training image. The one or more embodiments further include training the image translation network to translate images from the source visual domain to the target visual domain based on a calculated loss using the first and second training images.

Neural network for image style translation

This disclosure relates to methods, non-transitory computer readable media, and systems that use style-aware puppets patterned after a source-character-animation sequence to generate a target-character-animation sequence. In particular, the disclosed systems can generate style-aware puppets based on an animation character drawn or otherwise created (e.g., by an artist) for the source-character-animation sequence. The style-aware puppets can include, for instance, a character-deformational model, a skeletal-difference map, and a visual-texture representation of an animation character from a source-character-animation sequence. By using style-aware puppets, the disclosed systems can both preserve and transfer a detailed visual appearance and stylized motion of an animation character from a source-character-animation sequence to a target-character-animation sequence.

Generating target-character-animation sequences based on style-aware puppets patterned after source-character-animation sequences

Certain embodiments involve generating one or more of appearance guide and a positional guide and using one or more of the guides to synthesize a stylized image or animation. For example, a system obtains data indicating a target image and a style exemplar image. The system generates an appearance guide, a positional guide, or both from the target image and the style exemplar image. The system uses one or more of the guides to transfer a texture or style from the style exemplar image to the target image.

Generating a stylized image or stylized animation by matching semantic features via an appearance guide, a segmentation guide, and/or a temporal guide

Certain embodiments involve generating an appearance guide, a segmentation guide, and a positional guide and using one or more of the guides to synthesize a stylized image or animation. For example, a system obtains data indicating a target and a style exemplar image and generates a segmentation guide for segmenting the target image and the style exemplar image and identifying a feature of the target image and a corresponding feature of the style exemplar image. The system generates a positional guide for determining positions of the target feature and style feature relative to a common grid system. The system generates an appearance guide for modifying intensity levels and contrast values in the target image based on the style exemplar image. The system uses one or more of the guides to transfer a texture of the style feature to the corresponding target feature.

Techniques for illumination-guided example-based stylization of 3D renderings are described. In implementations, a source image and a target image are obtained, where each image includes a multi-channel image having at least a style channel and multiple light path expression (LPE) channels having light propagation information. Then, the style channel of the target image is synthesized to mimic a stylization of individual illumination effects from the style channel of the source image. As part of the synthesizing, the light propagation information is applied as guidance for synthesis of the style channel of the target image. Based on the guidance, the stylization of individual illumination effects from the style channel of the source image is transferred to the style channel of the target image. Based on the transfer, the style channel of the target image is then generated for display of the target image via a display device.

Illumination-guided example-based stylization of 3D renderings

Techniques for controlling patch-usage in image synthesis are described. In implementations, a curve is fitted to a set of sorted matching errors that correspond to potential source-to-target patch assignments between a source image and a target image. Then, an error budget is determined using the curve. In an example, the error budget is usable to identify feasible patch assignments from the potential source-to-target patch assignments. Using the error budget along with uniform patch-usage enforcement, source patches from the source image are assigned to target patches in the target image. Then, at least one of the assigned source patches is assigned to an additional target patch based on the error budget. Subsequently, an image is synthesized based on the source patches assigned to the target patches.

Controlling patch usage in image synthesis

Appearance transfer techniques are described in the following. In one example, a search and vote process is configured to select patches from the image exemplar and then search for a location in the target image that is a best fit for the patches. As part of this selection, a patch usage counter may also be employed in an example to ensure that selection of each of the patches from the image exemplar does not vary by more than one, one to another. In another example, transfer of an appearance of a boundary and interiors regions from the image exemplar to a target image is preserved.

Appearance transfer techniques

Appearance transfer techniques are described in the following that maintain temporal coherence between frames. In one example, a previous frame of a target video is warped that occurs in the sequence of the target video before a particular frame being synthesized. Color of the particular frame is transferred from an appearance of a corresponding frame of a video exemplar. In a further example, emitter portions are identified and addressed to preserve temporal coherence. This is performed to reduce an influence of the emitter portion of the target region in the selection of patches.

Growing community of inventors

Prague, Czechia

Daniel Sýkora