Spaces:
Running
Apply for community grant: Academic project (gpu)
We would like to share a demo for our academic work: "CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation"
Here is a brief introduction:
Recent CAPE works have produced object poses based on arbitrary keypoint definitions annotated on a user-provided support image. Our work departs from conventional CAPE methods, which require a support image, by adopting a text-based approach instead of the support image. Specifically, we use a pose-graph, where nodes represent keypoints that are described with text. This representation takes advantage of the abstraction of text descriptions and the structure imposed by the graph. Our approach effectively breaks symmetry, preserves structure, and improves occlusion handling. Under a 1-shot setting, our solution establishes a new state-of-the-art for CAPE.
Thanks in advance!
Thank you for the support!
Hi again
@hysts
,
While trying to properly configure and build the application, I changed the hardware back to CPU, as I thought that I would be able to get back to the ZeroGPU setting.
Unfortunately I can't assign ZeroGPU back to the project even though it seems that the project has a free ZeroGPU grant.
Could you please assign it back?
Thanks!