J
Jimei Yang
Researcher at Adobe Systems
Publications - 145
Citations - 18302
Jimei Yang is an academic researcher from Adobe Systems. The author has contributed to research in topics: Rendering (computer graphics) & Computer science. The author has an hindex of 52, co-authored 136 publications receiving 13213 citations. Previous affiliations of Jimei Yang include Chinese Academy of Sciences & University of California, Merced.
Papers
More filters
Patent
Editing digital images utilizing a neural network with an in-network rendering layer
TL;DR: In this article, a neural network is used to decompose an input digital image into intrinsic physical properties (e.g., material, illumination, and shape) and then a rendering layer is utilized to generate a modified digital image based on the target property and the remaining (unsubstituted) intrinsic physical property.
Patent
Labeling objects in image scenes
TL;DR: In this article, various methods for labeling objects using multi-scale partitioning, rare class expansion, and/or spatial context techniques are described. But none of these methods are suitable for the task of object detection.
Proceedings ArticleDOI
Exemplar Cut
TL;DR: This work presents a hybrid parametric and nonparametric algorithm, exemplar cut, for generating class-specific object segmentation hypotheses by solving a series of exemplar augmented graph cuts.
Proceedings ArticleDOI
Skeleton-free Pose Transfer for Stylized 3D Characters
TL;DR: This work presents the first method that automatically transfers poses between stylized 3D characters without skeletal rigging, and proposes a novel pose transfer network that predicts the character skinning weights and deformation transformations jointly to articulate the target character to match the desired pose.
Patent
Digital image completion using deep learning
TL;DR: In this paper, a generative adversarial network is used to generate a filled digital image with hole-filling content in place of holes and then the discriminative neural networks detect whether the filled digital images and the hole filling digital content correspond to or include computer-generated content.