Xin Lu
55Patents
9h-index
59Co-inventors
77Inventor score
Filing activity: Oct 1, 2010 → Apr 25, 2023
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US9760978B1 | Missing region prediction | Physics | 94 | Active |
| US10460214B2 | Deep salient content neural networks for efficient digital object segmentation | Physics | 33 | Active |
| USD957275S1 | Rangefinder | General | 17 | Active |
| US10089742B1 | Automatically segmenting images based on natural language phrases | Physics | 12 | Active |
| US9972092B2 | Utilizing deep learning for boundary-aware image segmentation | Physics | 11 | Active |
| US10915798B1 | Systems and methods for hierarchical webly supervised training for recognizing emotions in images | Physics | 11 | Active |
| US10614557B2 | Digital image completion using deep learning | Physics | 11 | Active |
| US10290085B2 | Image hole filling that accounts for global structure and local texture | Physics | 10 | Active |
| US10867416B2 | Harmonizing composite images using deep learning | Physics | 9 | Active |
| US10783622B2 | Training and utilizing an image exposure transformation neural network to generate a long-exposure image from a single short-exposure image | Physics | 9 | Active |
| US9613058B2 | Neural network image curation control | Physics | 7 | Active |
| US11335004B2 | Generating refined segmentation masks based on uncertain pixels | Physics | 7 | Active |
| US10521705B2 | Automatically selecting images using multicontext aware ratings | Electricity | 6 | Active |
| US9189834B2 | Adaptive denoising with internal and external patches | Physics | 5 | Active |
| US10755391B2 | Digital image completion by learning generation and patch matching jointly | Physics | 5 | Active |
| US9996768B2 | Neural network patch aggregation and statistics | Physics | 5 | Active |
| US9117262B2 | Learned piece-wise patch regression for image enhancement | Physics | 4 | Active |
| US10672164B2 | Predicting patch displacement maps using a neural network | Physics | 4 | Active |
| US10593043B2 | Utilizing deep learning for boundary-aware image segmentation | Physics | 4 | Active |
| US9122960B2 | Patch size adaptation for image enhancement | Physics | 3 | Active |
| US11250548B2 | Digital image completion using deep learning | Physics | 3 | Active |
| US10482639B2 | Deep high-resolution style synthesis | Physics | 3 | Active |
| US9767540B2 | Patch partitions and image processing | Physics | 3 | Active |
| US10410351B2 | Automatically segmenting images based on natural language phrases | Physics | 3 | Active |
| US10878575B2 | Foreground-aware image inpainting | Physics | 3 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.