MrNeRF (@janusch_patas)
2025-11-17 | โค๏ธ 638 | ๐ 78
Here is some new footage from this paper, offering a glimpse into the future of dynamic 3D Gaussian Splatting models combined with static reconstructed scenes.
Imagine this: when the lighting matches, the result becomes practically indistinguishable from reality. Just pick a scene, add characters, and record it from any angle. Apply diffusion models to instantly change the look.
I firmly believe this is the future of VFX.
๐ ์๋ณธ ๋งํฌ
๋ฏธ๋์ด
์ธ์ฉ ํธ์
MrNeRF (@janusch_patas)
AHA! Animating Human Avatars in Diverse Scenes with Gaussian Splatting
Contributions: โข We introduce the 3D Gaussian Splatting representation to the classical computer graphics problem of animating humans in 3D environments.
โข We demonstrate that our framework can be used for geometry-consistent free viewpoint rendering of monocular videos edited with new animated humans.
โข We introduce a novel Gaussian-aligned motion module for motion synthesis in scenes represented as 3D Gaussians.
โข We introduce a human scene Gaussian refinement optimization for the correct placement of human Gaussians in scenes represented using 3DGS, leading to better contact and interactions.
