Patents Assigned to Adobe Inc.
  • Publication number: 20260350909
    Abstract: Techniques for stochastic ray tracing for rendering digital assets are described and are implementable to efficiently render digital assets within scenes. In an example, a digital asset that includes transparent three-dimensional primitives is received to be included in a scene. Candidate intersections between a ray traced from a viewpoint within the scene and one or more of the primitives are identified. An intersection is selected from the candidate intersections based on binarized opacity values and distance values to the viewpoint determined for each of the candidate intersections. The digital asset is then rendered within the scene by applying a color value associated with the selected intersection to one or more pixels.
    Type: Application
    Filed: April 30, 2025
    Publication date: November 5, 2026
    Applicant: Adobe Inc.
    Inventors: Xin Sun, Yun Fei, Preetish Kakkar, Miloš Hašan, Jonathan Andrew Eisenmann, Iliyan Atanasov Georgiev, Fujun Luan
  • Publication number: 20260350968
    Abstract: In implementation of techniques for identifying repeating patterns, a computing device implements a pattern system to receive a digital image. The pattern system identifies a slice along a first axis of the digital image and a slice along a second axis of the digital image. The pattern system generates data describing pixel color along the slice along the first axis of the digital image and data describing pixel color along the slice along the second axis of the digital image. Based on the pixel color along the slice along the first axis and the pixel color along the slice along the second axis, the pattern system identifies a portion of the digital image depicting a visually repeating pattern.
    Type: Application
    Filed: April 30, 2025
    Publication date: November 5, 2026
    Applicant: Adobe Inc.
    Inventors: Arthur Jules Martin Roullier, Romain Pierre Rouffet, Jerome Eric Christophe Derel, Adrien Michel Paul Kaiser, Elena Garces Garcia
  • Publication number: 20260350863
    Abstract: Techniques for prompt-based image relighting and editing are described that support automatic generation of an edited digital image with high-fidelity and realistic lighting effects and background features. A processing device, for instance, receives as input a digital image that depicts a digital object, a lighting prompt, and a background prompt. The processing device generates a relit digital object that has a lighting condition specified by the lighting prompt applied to the digital object. The processing device further generates a background that includes a feature specified by the background prompt and the lighting condition. The processing device generates an edited digital object for output that includes the relit digital object and the background. The processing device further leverages a shadow synthesis model to edit shadows in the edited digital image. In this way, the techniques described herein preserve content details of the digital object when applying background and lighting effects.
    Type: Application
    Filed: July 8, 2026
    Publication date: November 5, 2026
    Applicant: Adobe Inc.
    Inventors: Ambareesh Revanur, Shradha Agrawal, Deepak Pai
  • Publication number: 20260350952
    Abstract: Techniques for using hybrid object constructions based on implicit and explicit representations are described. In an example, a processing device is operable to obtain a mesh that models an exterior surface of a simulated object, generate a neural representation of the exterior surface, and receive a user input that indicates a requested modification to one or more surface regions of the mesh. The processing device is further operable to incrementally update, using a machine-learning model, the surface regions of the mesh based on incremental changes applied by the machine-learning model to the neural representation for achieving the requested modification within corresponding portions of the exterior surface of the neural representation. The processing device is further operable to output the updated mesh for use in rendering the simulated object with the requested modification.
    Type: Application
    Filed: July 8, 2026
    Publication date: November 5, 2026
    Applicant: Adobe Inc.
    Inventors: Thibault Groueix, Vladimir Kim, Noam Aigerman, Amir Zvi Barda
  • Publication number: 20260349988
    Abstract: Change detection and updates using probabilistic data structures are described. In one or more examples, a change is detected to a dataset record that is used as a basis to generate a first sketch as a probabilistic data structure. A second sketch is generated as a probabilistic data structure based on the change to the dataset record. The first sketch is replaced with the second sketch as stored in a database, the database supporting a probabilistic result to a query operation.
    Type: Application
    Filed: July 14, 2026
    Publication date: November 5, 2026
    Applicant: Adobe Inc.
    Inventors: Sandeep Anant Nawathe, Yeshwanth Vijayakumar, Antonio Cuevas, Akhilesh Vedhera
  • Publication number: 20260350905
    Abstract: In implementing real-time parameterization of implicit surfaces, a processing device receives an implicit surface representing a three-dimensional (3D) object. The processing device approximates a geodesic path between one or more query points and a reference point on the implicit surface. Using the geodesic path, the processing device generates a parameterization patch on the implicit surface. The parameterization patch provides a localized two-dimensional (2D) coordinate system on a portion of the 3D object's surface. UV coordinates are generated for the query point based on the geodesic path.
    Type: Application
    Filed: April 30, 2025
    Publication date: November 5, 2026
    Applicant: Adobe Inc.
    Inventors: Jérémy Nicolas Levallois, Stephanie Wang, Pierre Gueth, Baptiste Louis Henry Genest
  • Publication number: 20260349995
    Abstract: In one aspect, a query management module executing on a processor receives, from a large language model (LLM), a graph query generated by the LLM based on a natural language query (NLQ). A validation module identifies an error in the graph query. The query management module provides an indication of the error to the LLM. The query management module receives a modified graph query from the LLM. The validation module validates the modified graph query. Based on the validation of the modified graph query, the query management module executes the modified graph query against a knowledge graph to return a result as a response to the NLQ.
    Type: Application
    Filed: June 26, 2026
    Publication date: November 5, 2026
    Applicant: Adobe Inc.
    Inventors: Ramasuri Narayanam, Chetan Sharma, Som Ranjan Satapathy, Siddhartha Kartikaye Goel, Shiv Kumar Saini, Shaddy Garg
  • Patent number: 12784411
    Abstract: Systems and methods for image editing are described. Embodiments of the present disclosure include obtaining an image and a prompt for editing the image. A diffusion model is tuned based on the image to generate different versions of the image. The prompt is then encoded to obtain a guidance vector, and the diffusion model generates a modified image based on the image and the encoded text prompt.
    Type: Grant
    Filed: November 8, 2022
    Date of Patent: November 3, 2026
    Assignee: ADOBE INC.
    Inventors: Yosef Gandelsman, Taesung Park, Richard Zhang, Elya Shechtman
  • Patent number: 12784139
    Abstract: Systems and methods for media generation are provided. According to one aspect, a method for media generation includes obtaining a media object and context data describing a context of the media object, wherein the media object comprises one or more modification parameters; generating a modified media object by adjusting the one or more modification parameters using a reinforcement learning model based on the context data; and providing the modified media object within the context.
    Type: Grant
    Filed: March 3, 2023
    Date of Patent: November 3, 2026
    Assignee: ADOBE INC.
    Inventors: Pooja Guhan, Saayan Mitra, Somdeb Sarkhel, Ritwik Sinha, Stefano Petrangeli, Viswanathan Swaminathan
  • Patent number: 12784140
    Abstract: Systems and methods are provided for image editing, and more particularly, for harmonizing background images with text. Embodiments of the present disclosure obtain an image including text and a region overlapping the text. In some aspects, the text includes a first color. Embodiments then select a second color that contrasts with the first color, and generate a modified image including the text and a modified region using a machine learning model that takes the image and the second color as input. The modified image is generated conditionally, so as to include the second color in a region corresponding to the text.
    Type: Grant
    Filed: June 14, 2023
    Date of Patent: November 3, 2026
    Assignee: ADOBE INC.
    Inventors: Ionut Mironicǎ, Marian Lupaşcu, Alexandru Vasile Costin, Cristian Catalin Buzoiu, Aliakbar Darabi
  • Patent number: 12786528
    Abstract: A method, apparatus, non-transitory computer readable medium, and system for generating a video clip includes obtaining an input video and a transcript of the input video, wherein the transcript comprises a plurality of sentences. In some cases, a language model is configured to generate a subset of the plurality of sentences based on the transcript. Additionally, the language model generates a video clip based on the input video and a subset of the plurality of sentences, wherein the video clip comprises a portion of the input video.
    Type: Grant
    Filed: October 15, 2024
    Date of Patent: November 3, 2026
    Assignee: ADOBE INC.
    Inventors: Rebecca Louise Croly, Hanieh Deilamsalehy, Stephen Joseph DiVerdi, Lubomira Assenova Dontcheva, Dingzeyu Li, Zhengyang Ma, Manas Singh, Rohit Suri, Emelie Olga Johanna Swerre, Anh Lan Truong, Pamela Zoni
  • Patent number: 12786137
    Abstract: Systems and methods for event processing are provided. One aspect of the systems and methods includes receiving an event corresponding to an interaction of a user with a digital content channel; identifying a rule state for a segmentation rule that assigns users to a segment; assigning the user to the segment by evaluating the segmentation rule based on the rule state and the event from the digital content channel; updating the rule state; and providing customized content to the user based on the assignment of the user to the segment.
    Type: Grant
    Filed: September 13, 2022
    Date of Patent: November 3, 2026
    Assignee: ADOBE INC.
    Inventors: John Thomas Kucera, Sandeep Nawathe
  • Patent number: 12784229
    Abstract: Systems and methods perform image matte generation using image bursts. In accordance with some aspects, an image burst comprising a set of images is received. Features of a reference image from the set of images is aligned with features of other images from the set of images. A matte for the reference image is generated using the aligned features.
    Type: Grant
    Filed: March 20, 2023
    Date of Patent: November 3, 2026
    Assignee: Adobe Inc.
    Inventors: Xuaner Zhang, Xinyi Wu, Markus Jamal Woodson, Joon-Young Lee, Brian Price, Jiawen Chen
  • Patent number: 12784230
    Abstract: In one implementation of subject-aware background video generation, a processing device generates mask data and foreground feature data from frames of a subject video. The mask data separates a subject depicted in the subject video from an environment therein. The foreground feature data describes the features of the subject. The processing device receives a condition frame that depicts a different environment. A machine-learning model generates a composite video by aligning the subject's movement with the different environment from inputs of the foreground feature data, the mask data, and the condition frame, which conditions the generation of the different environment for the composite video. The processing device then presents the composite video via a user interface.
    Type: Grant
    Filed: July 30, 2024
    Date of Patent: November 3, 2026
    Assignee: Adobe Inc.
    Inventors: Zhan Xu, Yang Zhou, Krishna Kumar Singh, Jimei Yang, Chun-hao Huang, Boxiao Pan
  • Publication number: 20260340355
    Abstract: Pose correlation based digital video generation is described. A plurality of reference digital images depicting a reference object and a plurality of target pose digital images depicting a target object are received. Reference features from the plurality of reference digital images and target features from the plurality of target pose digital images are extracted using one or more machine-learning models. A pose correlation map is computed, using the one or more machine-learning models, based on reference poses of the reference object from the plurality of reference digital images and target poses of the target object from the plurality of target pose digital images. A digital video is generated having a plurality of frames based on the reference features, the target features, and the pose correlation map and presented for display in a user interface.
    Type: Application
    Filed: April 22, 2025
    Publication date: October 29, 2026
    Applicant: Adobe Inc.
    Inventors: Zhan Xu, Zhixin Shu, Yang Zhou, Fating Hong, Duygu Ceylan Aksit
  • Publication number: 20260340839
    Abstract: In implementation of techniques for determining movement of passive physical interface controls, a computing device implements an interface system to receive a first image depicting a composite pattern formed by a first pattern overlapping a second pattern by a first amount, the first pattern incorporated onto a physical control. The interface system also receives a second image depicting a different composite pattern formed by the first pattern overlapping the second pattern by a second amount. Based on a comparison of the composite pattern and the different composite pattern, the interface system determines a displacement of the first pattern in relation to the second pattern. The interface system then performs an action based on the displacement.
    Type: Application
    Filed: April 29, 2025
    Publication date: October 29, 2026
    Applicant: Adobe Inc.
    Inventors: Chang Xiao, Eunyee Koh, Daniel De Jesus Campos Zamora, Alexa Fay Siu, Mustafa Doga Dogan
  • Publication number: 20260340941
    Abstract: In implementation of techniques for determining bounding volumes based on sphere carving, a computing device implements a sphere carving system to receive data indicating distances from points in space a surface of a three-dimensional object. The sphere carving system identifies a virtual representation that encloses the three-dimensional object. By iteratively removing portions between a surface of the virtual representation and the surface of the three-dimensional object, the sphere carving system generates a virtual shell based on a geometry of the three-dimensional object. The sphere carving system then outputs data related to the virtual shell.
    Type: Application
    Filed: April 29, 2025
    Publication date: October 29, 2026
    Applicant: Adobe Inc.
    Inventors: Axel Florent Jacques Paris, Thibaud Pierre Emilien Lambert, Theo Thonat, Hugo Amedee Schott
  • Patent number: 12776047
    Abstract: Various disclosed embodiments are directed to learning-free video object segmentation (VOS) of one or more video frames. In various instances, such VOS does not rely on human supervision or labeling and can be generalized or applied to any video “in the wild.” This is because training and fine-tuning are not required for VOS. Particular embodiments perform VOS based on feature similarity of different sections of a video frame and/or estimated motion similarity of different sections of the video frame, such as via a graph cut on a graph.
    Type: Grant
    Filed: August 9, 2023
    Date of Patent: October 27, 2026
    Assignee: Adobe Inc.
    Inventors: Silky Singh, Shirpad Deshmukh, Rishabh Jain, Mayur Hemani, Mausoom Sarkar, Balaji Krishnamurthy
  • Patent number: 12775694
    Abstract: In implementation of techniques for character entry pause time for passwords, a computing device implements a character entry pause system to present a user interface configured for password creation, the user interface including a plurality of options that are selectable via the user interface to set a corresponding pause time from a plurality of pause times between entry of characters of a password. The character entry pause system receives a first character of the password, a second character of the password, and a selected pause time from the plurality of options. The character entry pause system then stores the password including the selected pause time specified to occur between entry of the first character and the second character.
    Type: Grant
    Filed: November 20, 2024
    Date of Patent: October 27, 2026
    Assignee: Adobe Inc.
    Inventors: Nader Nassar, John A. Trammel, Christian Elgart
  • Patent number: 12776082
    Abstract: A method, apparatus, non-transitory computer readable medium, and system for image generation includes obtaining an input image and an input prompt. In some cases, the input image depicts a scene and the input prompt indicates a target element to be added to the scene. The image generation model generates a normalized output based on the input image and the input prompt by performing a channel shift on a preliminary output of the image generation model. A synthetic image is generated including the scene of the input image and the target element of the input prompt that is harmonized with the scene.
    Type: Grant
    Filed: August 16, 2024
    Date of Patent: October 27, 2026
    Assignee: ADOBE INC.
    Inventors: Zhe Lin, Yuqian Zhou, Krishna Kumar Singh