Matthias Niessner (@MattNiessner)
2025-04-17 | โค๏ธ 342 | ๐ 61
๐ข SHeaP: Self-Supervised Head Predictor Learned via 2D Gaussians ๐ข
Given a single input image, we predict accurate 3D head geometry, pose, and expression.
Previous works (e.g. DECA, EMOCA) use differentiable mesh rasterization to learn a self-supervised head geometry predictor via a photometric reconstruction loss. We borrow these ideas, but our key insight is to replace the mesh rendering with 2D Gaussian Splatting. This leads to much higher accuracy of the underlying predicted geometry and thus more gradient signal during training.
๐ https://nlml.github.io/sheap/ ๐ฅ https://www.youtube.com/watch?v=vhXsZJWCBMA&feature=youtu.be
Great work by @liamschoneveld @davidedavoli @jiapeng_tang
๐ ์๋ณธ ๋งํฌ
๋ฏธ๋์ด
๐ Related
Auto-generated - needs manual review
Tags
domain-vision-3d domain-rendering domain-ai-ml domain-visionos