MUMBAI, India, Aug. 31 -- Intellectual Property India has published a patent application (202514112779 A) filed by Robert Bosch Gmbh on November 17, 2025, for Homographic Deformed Cnn For Robust 3d Perception.
Inventors include Kumar, Abhinav; Zhao, Cheng; Ren, Liu; Wang, Ruoyu; Huang, Xinyu; and Guo, Yuliang.
The application for the patent was published on August 28, 2026, under issue no. 35/2026.
Abstract: A computer-implemented method and system relate to an image encoder (100) that receives a digital image (10) as input. The image encoder (100) generates a weight map (20) using a preceding feature map. The preceding feature map is generated using pixels of the digital image (10). The weight map (20) is generated based on lie data associated with the digital image (10). A homographic transformation is interpolated between two planar projections of the digital image (10) using at least the weight map (20) and a homography matrix. The homography matrix provides a mapping between the two planar projections of the digital image (10). Homographic transformed kernels are generated by applying the homographic transformation to convolution kernels. The homographic transformed kernels (22) are applied to the preceding feature map to conduct convolution on different plane regions appearing in the digital image (10) and generate a new feature map.
Disclaimer: Curated by HT Syndication.
