公开(公告)号：US20250045986A1

公开(公告)日：2025-02-06

申请号：US18365041

申请日：2023-08-03

Applicant: Adobe Inc.

Inventor： Tudor MUSCALU ,  Shashidhar MANGU ,  Piyush VASHISHT ,  Mrinalini SARDAR

IPC: G06T11/20 ,  G06T7/73

Abstract: Aspects of the technology described herein provide for a more precise generation of folded joints for objects rendered on a digital canvas. In an embodiment, segment points are received at the canvas from a user. From the segment points, structure points corresponding to vertices of the folded joint are identified. The structure points are connected to other identified structure points. The result is an object with a folded appearance, where the connections amongst the structure points form at least a portion of the object's perimeter.

公开(公告)号：US20230135694A1

公开(公告)日：2023-05-04

申请号：US17516964

申请日：2021-11-02

Applicant: Adobe Inc.

Inventor： Ankit PHOGAT ,  Matthew David FISHER ,  Vineet BATRA ,  Mrinalini SARDAR

IPC: G06T11/00 ,  G06T7/90 ,  G06T7/70 ,  G06T7/13

Abstract: Embodiments are disclosed for reconstructing freeform gradients from an input image. In particular, in one or more embodiments, the disclosed systems and methods comprise receiving an input image, computing an outline of the input image, identifying a set of candidate color handles for the input image, each candidate color handle of the set of candidate color handles representing an extremum point for a color in the input image, generating a reconstructed image using a subset of the set of candidate color handles, determining a reconstruction error by computing a difference between the input image and the reconstructed image, and providing the reconstructed image when the reconstruction error is below a threshold value.