NePu
Neural Puppeteer is an efficient neural rendering pipeline for articulated shapes. Through inverse rendering, it predicts 3D keypoints from multi-view 2D silhouettes without needing texture information. Additionally, this model can predict 3D keypoints for the same class of shapes using a single trained model. It also generalizes effectively from synthetic data training, as demonstrated by its success in zero-shot synthetic to real-world experiments. Furthermore, the neural rendering pipeline learns a global texture embedding which can be used in a downstream task to identify individuals.
About NePu
External Page
To view this content (source: www.xyz.de ), please click on Accept. We would like to point out that by accepting this iframe, data could be transmitted to third parties or cookies may be stored.
You can find more information on our privacy policy .
External Page
To view this content (source: www.xyz.de ), please click on Accept. We would like to point out that by accepting this iframe, data could be transmitted to third parties or cookies may be stored.
You can find more information on our privacy policy .
Related publications
- Giebenhain, S., Waldmann, U., Johannsen, O., Goldlücke, B. (2022) Neural Puppeteer: Keypoint-Based Neural Rendering of Dynamic Shapes. Proceedings of the Asian Conference on Computer Vision (ACCV), 2022, pp. 2830-2847.
- Waldmann, U., Johannsen, O., Goldlücke, B. (2024) Neural Texture Puppeteer: A Framework for Neural Geometry and Texture Rendering of Articulated Shapes, Enabling Re-Identification at Interactive Speed. Proceedings of the IEEE/CVF WACV Workshops, pp. 69-79