Sensitive content

This media may contain sensitive content.

正在加载视频...

视频加载失败

For this simulation I used the algorithm I invented, to generate a mesh around a set of physics particles. The particles are used as bones. Skinned mesh math runs on GPU, updates the mesh, then it's rendered, without any data sent GPU->CPU. Marching cubes would be easier though.

258,545 次观看 • 1 年前 •via X (Twitter)

10 条评论

The Water Museum 的头像
The Water Museum1 年前

Cut them in half

Rainmaker 的头像
Rainmaker2 年前

Can Machine Learning beat the market? Check out this post on my free Substack where I share code and commentary for an XGBoost model and a Random Forest model that both deliver powerful performances.

Diogenes of Cyberborea 的头像
Diogenes of Cyberborea1 年前

does this simulation support VR?

Zolden 的头像
Zolden1 年前

What's the point, there's no haptic gloves yet, that would let us touch those.

David Shapiro ⏩ 的头像
David Shapiro ⏩1 年前

Anime physics lol

Zolden 的头像
Zolden1 年前

Yeah, the physics aren't extremely boobies-alike/ Probably an artist could modify the physics properties until the simulation imitates real boobies more realistically.

огурец мозга 的头像
огурец мозга1 年前

Хе-хе сиська

Ilia Prokhorov (DemensDeum) 的头像
Ilia Prokhorov (DemensDeum)1 年前

art

Carlos Pinheiro 的头像
Carlos Pinheiro1 年前

I think the nipples should get hard, too, with all of this interaction 😁

EDG 的头像
EDG1 年前

Joder, buenas tetas.

相关视频

[NeurIPS '24] DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation Abstract (excerpt) We introduce DreamMesh4D, a novel framework that combines mesh representation with sparse-controlled deformation technique to generate high-quality 4D object from a monocular video. To overcome the limitation of classical texture representation, we bind Gaussian splats to the surface of the triangular mesh for differentiable optimization of both the texture and mesh vertices. In particular, DreamMesh4D begins with a coarse mesh provided by a single image based 3D generation method. Sparse points are then uniformly sampled across the surface of the mesh, and are used to build a deformation graph to drive the motion of the 3D object for the sake of computational efficiency and providing additional constraint. For each step, transformations of sparse control points are predicted using a deformation network, and the mesh vertices as well as the bound surface Gaussians are deformed via a geometric skinning algorithm. The skinning algorithm is a hybrid approach combining LBS (linear blending skinning) and DQS (dual-quaternion skinning), mitigating drawbacks associated with both approaches. The static surface Gaussians and mesh vertices as well as the dynamic deformation network are learned via reference view photometric loss, score distillation loss as well as other regularization losses in a two-stage manner. Extensive experiments demonstrate that our method outperforms prior video-to-4D generation methods in terms of rendering quality and spatial-temporal consistency.

MrNeRF

12,323 次观看 • 1 年前