正在加载视频...
视频加载失败
Our new work PSHuman reconstructs a detailed 3D human mesh from a single-view image in ~1min. Codes have already been released! Welcome to try it! Project page: Codes: Paper:
10 条评论

The key idea is to adopt the multiview diffusion to generate novel-view images and normal maps. Then, we apply inverse rendering techniques to reconstruct the textured human meshes. We improve face reconstruction with a global-local denoising scheme.

incredible work

Great! I tried to replicate my wife in blender modifying a human model, now i suppose i'd just have to take a pic of her in A-pose, use PSHuman then add bones/rig in blender? 😃

What's the novelty compared to any image to mesh techniques which exist today? Also I'm seeing a bunch of seam artifacts on the textures

We add SMPL skeletons to guide the diffusion process, generate 6 novel-view images, and improve the face regions with a new denoiser. The multiview-to-mesh reconstruction follows Unique3D but initializes from SMPL.

Now do that for cats please

can this be ported to say fbx format? say unreal engine's metahuman face and body?

We are not so familiar with UE and probably cannot support it. This may not be directly applicable to Game development, which still requires additional efforts in remeshing, animation, etc.😊

Dark mode for this paper 🌚

Anywhere a user can try?

