ASH: Animatable Gaussian Splats for Efficient and Photoreal Human Rendering
This addresses the problem of efficient and controllable human avatar rendering for applications in computer vision and graphics, representing a significant advance over prior real-time methods.
The paper tackles real-time photorealistic rendering of dynamic human avatars by proposing ASH, an animatable Gaussian splatting method that parameterizes humans as 3D Gaussians attached to a deformable model and learns parameters in 2D texture space, resulting in outperforming existing real-time methods by a large margin and achieving comparable or better results than offline methods.
Real-time rendering of photorealistic and controllable human avatars stands as a cornerstone in Computer Vision and Graphics. While recent advances in neural implicit rendering have unlocked unprecedented photorealism for digital avatars, real-time performance has mostly been demonstrated for static scenes only. To address this, we propose ASH, an animatable Gaussian splatting approach for photorealistic rendering of dynamic humans in real-time. We parameterize the clothed human as animatable 3D Gaussians, which can be efficiently splatted into image space to generate the final rendering. However, naively learning the Gaussian parameters in 3D space poses a severe challenge in terms of compute. Instead, we attach the Gaussians onto a deformable character model, and learn their parameters in 2D texture space, which allows leveraging efficient 2D convolutional architectures that easily scale with the required number of Gaussians. We benchmark ASH with competing methods on pose-controllable avatars, demonstrating that our method outperforms existing real-time methods by a large margin and shows comparable or even better results than offline methods.