Geometry Enhancements from Visual Content: Going Beyond Ground Truth
This work addresses the problem of improving the resolution of low-cost depth sensors for applications requiring detailed 3D models.
This paper introduces a cyclic architecture that extracts high-frequency patterns from images and re-inserts them as geometric features. This method enhances the resolution of low-cost depth sensors, capturing fine details while remaining faithful to the scanned ground truth, and achieves state-of-the-art results for depth super-resolution.
This work presents a new cyclic architecture that extracts high-frequency patterns from images and re-insert them as geometric features. This procedure allows us to enhance the resolution of low-cost depth sensors capturing fine details on the one hand and being loyal to the scanned ground truth on the other. We present state-of-the-art results for depth super-resolution tasks and as well as visually attractive, enhanced generated 3D models.