Adobe, Inc.

Stripe, Inc.

University of Massachusetts

Matthew David Fisher

Vineet Batra

Ankit Phogat

Praveen Kumar Dhanuka

Arushi Jain

Vladimir Kim

Jonathan Eisenmann

Elya Shechtman

Daniel Max Kaufman

Oliver Wang

Tarun Beri

Mridul Kavidayal

Zhaowen Wang

Kevin Wampler

Bryan Russell

Deepali Aneja

Hailin Jin

Jingwan Lu

Richard Zhang

Ashish Goel

Zhifei Zhang

Geoffrey Oxholm

Peter Lofgren

Pranav Dandekar

Souymodip Chakraborty

Wenqi Xian

Evangelos Kalogerakis

Zhe Lin

Kalyan Krishna Sunkavalli

Sunil Sharadchandra Hadap

Aaron Phillip Hertzmann

Emiliano Gambaretto

Yannick Hold-Geoffroy

Wilmot Li

Michal Lukac

Sumit Dhingra

Ashwani Chandil

Mrinalini Sardar

Chen-Hsuan Lin

Difan Liu

Vijit Saxena

Vineet Agarwal

Pierre-alain Langlois

Yang Zhou

Yijun Li

Federico Perazzi

Niloy Jyoti Mitra

Taesung Park

Noam Aigerman

Sameer Bhatt

Vivek Agrawal

Siddhartha Chaudhuri

John Nelson

Michal Lukác

Michael Gharbi

Daniel Glen Hopkins

Dwight L Allen

Nishant Kumar

Vikas Sharma

Omid Poursaeed

Tobias Hinz

Hung-Yu Tseng

Krishna Bhargava Mullia Lakshminarayana

Dean A Hopkins

Samaneh Azadi

Shantanu Agarwal

Seungjoo Yoo

Anuradha Yadav

Xuan Li

Chinthala Pradyumna Reddy

Zhan Xu

Sanjeev Muralikrishnan

Rupali Arora

Manuel Rodriguez Ladron De Guevara

Mustafa Isik

Steven Malekos

Nimesh Shukla

A stroke-guided vectorization system is described that generates, from an input sketch and guide image depicting an approximate vector representation of the sketch, an aligned guide image depicting an improved vector representation of the sketch. To do so, the stroke-guided vectorization system determines black levels representing a vector stroke in the input sketch and white levels representing a background in the input sketch. The stroke-guided vectorization system determines a black threshold value and a white threshold value for discrete portions of the aligned guide image using subsets of the black levels and subsets of the white levels determined using the input sketch. Each discrete portion of the aligned guide image is then mapped to a vector stroke or a background based on the black threshold value and the white threshold value of the portion.

Stroke-guided sketch vectorization

Embodiments are disclosed for reconstructing linear gradients from an input image that can be applied to another image. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving a raster image, the raster image including a representation of a linear color gradient. The disclosed systems and methods further comprise determining a vector representing a direction of the linear color gradient. The disclosed systems and methods further comprise analyzing pixel points along the direction of the linear color gradient to compute color stops of the linear color gradient. The disclosed systems and methods further comprise generating an output color gradient vector with the computed color stops of the linear color gradient, the output color gradient vector to be applied to a vector graphic.

Reconstructing linear gradients

Methods, systems, and non-transitory computer readable storage media are disclosed for utilizing a multi-stroke neural network for modifying a digital image via a plurality of generated stroke parameters in a single pass of the neural network. Specifically, the disclosed system utilizes an encoder neural network to generate an encoding of a digital image. The disclosed system then utilizes a decoder neural network that generates a sequence of stroke parameters for digital drawing strokes from the encoding in a single pass of the encoder neural network and decoder neural network. Additionally, the disclosed system utilizes a renderer neural network to render the digital drawing strokes on a digital canvas according to the sequence of stroke parameters. In additional embodiments, the disclosed system utilizes a balance of loss functions to learn parameters of the multi-stroke neural network to generate stroke parameters according to various rendering styles.

Generating stylized digital images via drawing stroke optimization utilizing a multi-stroke neural network

Semantic fill techniques are described that support generating fill and editing images from semantic inputs. A user input, for example, is received by a semantic fill system that indicates a selection of a first region of a digital image and a corresponding semantic label. The user input is utilized by the semantic fill system to generate a guidance attention map of the digital image. The semantic fill system leverages the guidance attention map to generate a sparse attention map of a second region of the digital image. A semantic fill of pixels is generated for the first region based on the semantic label and the sparse attention map. The edited digital image is displayed in a user interface.

Semantic image fill at high resolutions

Methods, systems, and non-transitory computer readable storage media are disclosed for automatically detecting and reconstructing patterns in digital images. The disclosed system determines structurally similar pixels of a digital image by comparing neighborhood descriptors that include the structural context for neighborhoods of the pixels. In response to identify structurally similar pixels of a digital image, the disclosed system utilizes non-maximum suppression to reduce the set of structurally similar pixels to collinear pixels within the digital image. Additionally, the disclosed system determines whether a group of structurally similar pixels define the boundaries of a pattern cell that forms a rectangular grid pattern within the digital image. The disclosed system also modifies a boundary of a detected pattern cell to include a human-perceived pattern object via a sliding window corresponding to the pattern cell.

Detecting and recovering patterns in digital raster images

Systems and methods for image processing are described. Embodiments of the present disclosure receive a raster image depicting a radial color gradient; compute an origin point of the radial color gradient based on an orthogonality measure between a color gradient vector at a point in the raster image and a relative position vector between the point and the origin point; construct a vector graphics representation of the radial color gradient based on the origin point; and generate a vector graphics image depicting the radial color gradient based on the vector graphics representation.

Reconstructing concentric radial gradients

Generating a vector representation of a hand-drawn sketch is described. To do so, the sketch is segmented into different superpixel regions. Superpixels are grown by distributing superpixel seeds throughout an image of the sketch and assigning unassigned pixels to a neighboring superpixel based on pixel value differences. The border between each pair of adjacent superpixels is then classified as either an active or an inactive boundary, with active boundaries indicating that the border corresponds to a salient sketch stroke. Vector paths are generated by traversing edges between pixel vertices along the active boundaries. To minimize vector paths included in the vector representation, vector paths are greedily generated first for longer curves along active boundaries until each edge is assigned to a vector path. Regions encompassed by vector paths corresponding to a foreground superpixel are filled to produce a high-fidelity vector representation of the sketch.

Curve generation for sketch vectorization

Systems and methods for image processing are described. Embodiments of the present disclosure include receiving a raster image depicting a radial color gradient; computing a radial disk model for the radial color gradient, wherein the radial disk model defines a plurality of disks with centers aligned in a same direction; constructing a vector graphics representation of the radial color gradient based on the radial disk model; and generating a vector graphics image depicting the radial color gradient based on the vector graphics representation.

Reconstructing general radial gradients

Techniques for vector object blending are described to generate a transformed vector object based on a first vector object and a second vector object. A transformation module, for instance, receives a first vector object that includes a plurality of first paths and a second vector object that includes a plurality of second paths. The transformation module computes morphing costs based on a correspondence within candidate path pairs that include one of the first paths and one of the second paths. Based on the morphing costs, the transformation module generates a low-cost mapping of paths between the first paths and the second paths. To generate the transformed vector object, the transformation module adjusts one or more properties of at least one of the first paths based on the mapping, such as geometry, appearance, and z-order.

Vector object blending

Embodiments are disclosed for generating multiple color theme variations from an input image using learned color distributions. A method of generating multiple color theme variations from an input image using learned color distributions includes obtaining, by a user interface manager, an input image, determining, by a color extraction manager, one or more color priors based on the input image, generating, by a color distribution modeling network, a plurality of color theme variations based on the one or more color priors, ranking, by a color theme evaluation network, the plurality of color theme variations, and generating, by a recolor manager, a plurality of recolored output images using the plurality of color theme variations.

Multimodal color variations using learned color distributions

An information preservation and conveyance system for providing information and effects to intelligent creatures in the future. The system provides durable containers with components secured inside and durable structure components, such as building bricks for example, mountable to a durable building, pyramid, or other structure, with at least one structure component having external surface information readable by a human. Higher density durable information providing components may be secured inside a durable container by resilient devices to absorb impact forces. Durable optical magnifier pictographic instructions and an optical magnifier or projector may be secured by durable containers, which can have a container opener durably mounted to exposed sections on the durable containers. The durable containers can contain audio generation apparatus, which optionally may teach a language, and any of a wide variety of types of information and articles of possible interest and value to a discoverer in the future.

Information preservation and conveyance system and method of use

A plurality of pixel-based sampling points are identified within an image, wherein sampling points of a pixel are distributed within the pixel. For individual sampling points of individual pixels, a corresponding radiance vector is estimated. A radiance vector includes one or more radiance values characterizing light received at a sampling point. A first machine learning module generates, for each pixel, a corresponding intermediate radiance feature vector, based on the radiance vectors associated with the sampling points within that pixel. A second machine learning module generates, for each pixel, a corresponding final radiance feature vector, based on an intermediate radiance feature vector for that pixel, and one or more other intermediate radiance feature vectors for one or more other pixels neighboring that pixel. One or more kernels are generated, based on the final radiance feature vectors, and applied to corresponding pixels of the image, to generate a lower noise image.

Denoising images rendered using Monte Carlo renderings

The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately and flexibly generating scalable and semantically editable font representations utilizing a machine learning approach. For example, the disclosed systems generate a font representation code from a glyph utilizing a particular neural network architecture. For example, the disclosed systems utilize a glyph appearance propagation model and perform an iterative process to generate a font representation code from an initial glyph. Additionally, using a glyph appearance propagation model, the disclosed systems automatically propagate the appearance of the initial glyph from the font representation code to generate additional glyphs corresponding to respective glyph labels. In some embodiments, the disclosed systems propagate edits or other changes in appearance of a glyph to other glyphs within a glyph set (e.g., to match the appearance of the edited glyph).

Generating scalable and semantically editable font representations

The present disclosure relates to systems, methods, and non-transitory computer-readable media that merge separate digital point text objects into a single merged digital text object while preserving the properties and original visual appearance associated with the digital text included therein. For example, the disclosed systems can determine point text character properties associated with the separate digital point text objects (e.g., rotations, baseline shifts, etc.). The disclosed systems can merge the separate digital point text objects into a single merged digital point text object and modify associated font character properties to reflect the determined point text character properties. Further, the disclosed systems can generate an area text object based on the merged digital point text object where the area text object includes the digital text and the font character properties.

Merging selected digital point text objects

Techniques for generating a stylized drawing of three-dimensional (3D) shapes using neural networks are disclosed. A processing device generates a set of vector curve paths from a viewpoint of a 3D shape; extracts, using a first neural network of a plurality of neural networks of a machine learning model, surface geometry features of the 3D shape based on geometric properties of surface points of the 3D shape; determines, using a second neural network of the plurality of neural networks of the machine learning model, a set of at least one predicted stroke attribute based on the surface geometry features and a predetermined drawing style; generates, based on the at least one predicted stroke attribute, a set of vector stroke paths corresponding to the set of vector curve paths; and outputs a two-dimensional (2D) stylized stroke drawing of the 3D shape based at least on the set of vector stroke paths.

Generation of stylized drawing of three-dimensional shapes using neural networks

Growing community of inventors

Palo Alto, CA, United States of America

Matthew David Fisher