James Imber
32Patents
3h-index
18Co-inventors
56Inventor score
Filing activity: Sep 3, 2013 → Jan 29, 2024
Most-cited inventions
| Patent | Title | Area | Cited by | Status |
|---|---|---|---|---|
| US11144819B2 | Convolutional neural network hardware configuration | Physics | 10 | Active |
| US9875554B2 | Surface normal estimation for use in rendering an image | Physics | 6 | Active |
| US9607429B2 | Relightable texture for use in rendering an image | Physics | 4 | Active |
| US11392823B2 | Error allocation format selection for hardware implementation of deep neural network | Physics | 3 | Active |
| US9959636B2 | Systems and methods for processing images of objects using global lighting estimates | Physics | 2 | Active |
| US10885427B2 | Error allocation format selection for hardware implementation of deep neural network | Physics | 2 | Active |
| US10157446B2 | Systems and methods for processing images of objects using interpolation between keyframes | Physics | 1 | Active |
| US9613431B2 | Local irradiance estimation for use in rendering an image | Physics | 1 | Active |
| US12198307B2 | Rendering an image of a 3-D scene using guided image filtering | Physics | 0 | Active |
| US9911200B2 | Determining diffuse image component values for use in rendering an image | Physics | 0 | Active |
| US12175349B2 | Hierarchical mantissa bit length selection for hardware implementation of deep neural network | Physics | 0 | Active |
| US10223827B2 | Relightable texture for use in rendering an image | Physics | 0 | Active |
| US10181183B2 | Systems and methods for processing images of objects using coarse intrinsic colour estimates | Physics | 0 | Active |
| US11443414B2 | Image signal processing | Physics | 0 | Active |
| US12020145B2 | End-to-end data format selection for hardware implementation of deep neural networks | Physics | 0 | Active |
| US11915397B2 | Rendering an image of a 3-D scene | Physics | 0 | Active |
| US12056600B2 | Histogram-based per-layer data format selection for hardware implementation of deep neural network | Physics | 0 | Active |
| US11593626B2 | Histogram-based per-layer data format selection for hardware implementation of deep neural network | Physics | 0 | Active |
| US11625581B2 | Hardware implementation of a convolutional neural network | Physics | 0 | Active |
| US9418473B2 | Relightable texture for use in rendering an image | Physics | 0 | Active |
| US11636306B2 | Implementing traditional computer vision algorithms as neural networks | Physics | 0 | Active |
| US11948070B2 | Hardware implementation of a convolutional neural network | Physics | 0 | Active |
| US10185888B2 | Systems and methods for processing images of objects using lighting keyframes | Physics | 0 | Active |
| US11556613B2 | Methods and systems for implementing a convolution transpose layer of a neural network | Physics | 0 | Active |
| US11734553B2 | Error allocation format selection for hardware implementation of deep neural network | Physics | 0 | Active |
Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.