Abstract: Generative shape creation and editing is leveraged in a digital medium environment. An object editor system represents a set of training shapes as sets of visual elements known as “handles,” and converts sets of handles into signed distance field (SDF) representations. A handle processor model is then trained using the SDF representations to enable the handle processor model to generate new shapes that reflect salient visual features of the training shapes. The trained handle processor model, for instance, generates new sets of handles based on salient visual features learned from the training handle set. Thus, utilizing the described techniques, accurate characterizations of a set of shapes can be learned and used to generate new shapes. Further, generated shapes can be edited and transformed in different ways.

Abstract: Image modification using detected symmetry is described. In example implementations, an image modification module detects multiple local symmetries in an original image by discovering repeated correspondences that are each related by a transformation. The transformation can include a translation, a rotation, a reflection, a scaling, or a combination thereof. Each repeated correspondence includes three patches that are similar to one another and are respectively defined by three pixels of the original image. The image modification module generates a global symmetry of the original image by analyzing an applicability to the multiple local symmetries of multiple candidate homographies contributed by the multiple local symmetries. The image modification module associates individual pixels of the original image with a global symmetry indicator to produce a global symmetry association map.

Abstract: A multi-layer light source includes an emissive layer and a textured lighting gel layer, the lighting gel layer being situated between the emissive layer and a 2D canvas or a 3D object. User inputs controlling the multi-layer light source are received, these user inputs being provided with the user interacting with the 2D canvas without switching to editing in 3D space. The multi-layer light source is configured based on the user inputs and, based on the configuration, emission of light rays from the multi-layer light source is determined. Areas of shadows cast by 3D objects are also determined. An image generation system determines, a color of a location (e.g., a pixel) on the 2D canvas or the 3D object that a light ray intersects based on the color that is in the lighting gel layer that the light ray passes through.

Abstract: A multi-layer light source includes an emissive layer and a textured lighting gel layer, the lighting gel layer being situated between the emissive layer and a 2D canvas or a 3D object. User inputs controlling the multi-layer light source are received, these user inputs being provided with the user interacting with the 2D canvas without switching to editing in 3D space. The multi-layer light source is configured based on the user inputs and, based on the configuration, emission of light rays from the multi-layer light source is determined. Areas of shadows cast by 3D objects are also determined. An image generation system determines, a color of a location (e.g., a pixel) on the 2D canvas or the 3D object that a light ray intersects based on the color that is in the lighting gel layer that the light ray passes through.

Abstract: Generative shape creation and editing is leveraged in a digital medium environment. An object editor system represents a set of training shapes as sets of visual elements known as “handles,” and converts sets of handles into signed distance field (SDF) representations. A handle processor model is then trained using the SDF representations to enable the handle processor model to generate new shapes that reflect salient visual features of the training shapes. The trained handle processor model, for instance, generates new sets of handles based on salient visual features learned from the training handle set. Thus, utilizing the described techniques, accurate characterizations of a set of shapes can be learned and used to generate new shapes. Further, generated shapes can be edited and transformed in different ways.

Abstract: Various embodiments enable curves to be drawn around 3-D objects by intelligently determining or inferring how the curve flows in the space around the outside of the 3-D object. The various embodiments enable such curves to be drawn without having to constantly rotate the 3-D object. In at least some embodiments, curve flow is inferred by employing a vertex position discovery process, a path discovery process, and a final curve construction process.

Abstract: Generative shape creation and editing is leveraged in a digital medium environment. An object editor system represents a set of training shapes as sets of visual elements known as “handles,” and converts sets of handles into signed distance field (SDF) representations. A handle processor model is then trained using the SDF representations to enable the handle processor model to generate new shapes that reflect salient visual features of the training shapes. The trained handle processor model, for instance, generates new sets of handles based on salient visual features learned from the training handle set. Thus, utilizing the described techniques, accurate characterizations of a set of shapes can be learned and used to generate new shapes. Further, generated shapes can be edited and transformed in different ways.

Abstract: Images are rendered from deeply learned raytracing parameters. Active learning, via a machine learning (ML) model (e.g., implemented by a deep neural network), is used to automatically determine, infer, and/or predict optimized, or at least somewhat optimized, values for parameters used in raytracing methods. Utilizing deep learning to determine optimized, or at least somewhat optimized, values for raytracing parameters is in contrast to conventional methods, which require users to rely of heuristics for parameter value setting. In various embodiments, one or more parameters regarding the termination and splitting of traced light paths in stochastic-based (e.g., Monte Carlo) raytracing are determined via active learning. In some embodiments, one or more parameters regarding the sampling rate of shadow rays are also determined.

Abstract: Embodiments of the present invention are directed towards compactly incorporating texture charts into a texture atlas. Texture charts represent three-dimensional mesh segments flattened into two-dimensional shapes. In one embodiment, a texture atlas generating engine is used to generate and evaluate compactness scores of candidate placements for a texture chart. Candidate placements generally refer to the possible locations where a texture chart can be incorporated into a texture atlas. The compactness score can be based on minimizing the distance between a texture chart being incorporated into the texture atlas and the center of mass of previously incorporated texture charts within a texture atlas. In embodiments, an infinity norm can be utilized to compute such a compactness score by outputting an average length of vectors between a texture chart being incorporated into a texture atlas and the texture atlas. Other embodiments may be described and/or claimed.

Abstract: Images are rendered from deeply learned raytracing parameters. Active learning, via a machine learning (ML) model (e.g., implemented by a deep neural network), is used to automatically determine, infer, and/or predict optimized, or at least somewhat optimized, values for parameters used in raytracing methods. Utilizing deep learning to determine optimized, or at least somewhat optimized, values for raytracing parameters is in contrast to conventional methods, which require users to rely of heuristics for parameter value setting. In various embodiments, one or more parameters regarding the termination and splitting of traced light paths in stochastic-based (e.g., Monte Carlo) raytracing are determined via active learning. In some embodiments, one or more parameters regarding the sampling rate of shadow rays are also determined.

Abstract: Various embodiments enable curves to be drawn around 3-D objects by intelligently determining or inferring how the curve flows in the space around the outside of the 3-D object. The various embodiments enable such curves to be drawn without having to constantly rotate the 3-D object. In at least some embodiments, curve flow is inferred by employing a vertex position discovery process, a path discovery process, and a final curve construction process.

Abstract: Image modification using detected symmetry is described. In example implementations, an image modification module detects multiple local symmetries in an original image by discovering repeated correspondences that are each related by a transformation. The transformation can include a translation, a rotation, a reflection, a scaling, or a combination thereof. Each repeated correspondence includes three patches that are similar to one another and are respectively defined by three pixels of the original image. The image modification module generates a global symmetry of the original image by analyzing an applicability to the multiple local symmetries of multiple candidate homographies contributed by the multiple local symmetries. The image modification module associates individual pixels of the original image with a global symmetry indicator to produce a global symmetry association map.

Abstract: Various embodiments enable curves to be drawn around 3-D objects by intelligently determining or inferring how the curve flows in the space around the outside of the 3-D object. The various embodiments enable such curves to be drawn without having to constantly rotate the 3-D object. In at least some embodiments, curve flow is inferred by employing a vertex position discovery process, a path discovery process, and a final curve construction process.

Abstract: Image modification using detected symmetry is described. In example implementations, an image modification module detects multiple local symmetries in an original image by discovering repeated correspondences that are each related by a transformation. The transformation can include a translation, a rotation, a reflection, a scaling, or a combination thereof. Each repeated correspondence includes three patches that are similar to one another and are respectively defined by three pixels of the original image. The image modification module generates a global symmetry of the original image by analyzing an applicability to the multiple local symmetries of multiple candidate homographies contributed by the multiple local symmetries. The image modification module associates individual pixels of the original image with a global symmetry indicator to produce a global symmetry association map.

Abstract: Techniques and systems are described that support light path correlation in digital image rendering of a digital scene. In one example, a plurality of light paths between a light source and the digital image to be rendered of a digital scene are identified by a computing device. Each light path of the plurality of light paths includes a primary vertex and a secondary vertex between respective segments of the light path. A plurality of correlated samples is then generated by the computing device from the light paths. Each correlated sample of the plurality of correlated samples is based at least in part on similarity of the secondary vertex of respective said light paths to each other, e.g., on location, geometric normal, or surface material properties. The digital image of the digital scene is then rendered by the computing device based at least in part on the plurality of correlated samples.

Abstract: Embodiments of the present invention are directed towards compactly incorporating texture charts into a texture atlas. Texture charts represent three-dimensional mesh segments flattened into two-dimensional shapes. In one embodiment, a texture atlas generating engine is used to generate and evaluate compactness scores of candidate placements for a texture chart. Candidate placements generally refer to the possible locations where a texture chart can be incorporated into a texture atlas. The compactness score can be based on minimizing the distance between a texture chart being incorporated into the texture atlas and the center of mass of previously incorporated texture charts within a texture atlas. In embodiments, an infinity norm can be utilized to compute such a compactness score by outputting an average length of vectors between a texture chart being incorporated into a texture atlas and the texture atlas. Other embodiments may be described and/or claimed.

Abstract: Embodiments of the present invention are directed towards compactly incorporating texture charts into a texture atlas. Texture charts represent three-dimensional mesh segments flattened into two-dimensional shapes. In one embodiment, a texture atlas generating engine is used to generate and evaluate compactness scores of candidate placements for a texture chart. Candidate placements generally refer to the possible locations where a texture chart can be incorporated into a texture atlas. The compactness score can be based on minimizing the distance between a texture chart being incorporated into the texture atlas and the center of mass of previously incorporated texture charts within a texture atlas. In embodiments, an infinity norm can be utilized to compute such a compactness score by outputting an average length of vectors between a texture chart being incorporated into a texture atlas and the texture atlas. Other embodiments may be described and/or claimed.

Abstract: Digital image animation techniques are described. In one example, animations are used for a single digital image to permit movement or other effects to be exhibited as part of the digital image without requiring multiple frames as in conventional techniques. Transformation of the single digital image by the animations may also be coordinated, such as to synchronize or not synchronize movement of objects to promote realism. In another example, portions and even an entirety of these techniques may be performed automatically and without user intervention. Machine learning, for instance, may be employed using a neural network to classify the digital image into one or more semantic classes. The semantic classes may then be used to recommend animations to transform the digital image.

Abstract: Various embodiments enable curves to be drawn around 3-D objects by intelligently determining or inferring how the curve flows in the space around the outside of the 3-D object. The various embodiments enable such curves to be drawn without having to constantly rotate the 3-D object. In at least some embodiments, curve flow is inferred by employing a vertex position discovery process, a path discovery process, and a final curve construction process.

Abstract: Techniques and systems are described that support light path correlation in digital image rendering of a digital scene. In one example, a plurality of light paths between a light source and the digital image to be rendered of a digital scene are identified by a computing device. Each light path of the plurality of light paths includes a primary vertex and a secondary vertex between respective segments of the light path. A plurality of correlated samples is then generated by the computing device from the light paths. Each correlated sample of the plurality of correlated samples is based at least in part on similarity of the secondary vertex of respective said light paths to each other, e.g., on location, geometric normal, or surface material properties. The digital image of the digital scene is then rendered by the computing device based at least in part on the plurality of correlated samples.