Loading video...

Video Failed to Load

Go Home

๐Ÿš€ Introducing #DreamCraft3D, our breakthrough hierarchical technique for 3D content generation. Leading the way in AIGC, we're redefining 3D generation: Project page: Paper: Code:

16,400 views โ€ข 2 years ago โ€ขvia X (Twitter)

10 Comments

muhammed rekani's profile picture
muhammed rekani1 year ago

Who is here after the R1 storm ๐Ÿ˜‚

Adams Pro ๐• ๐Ÿ‘จโ€๐Ÿ’ป๐Ÿ‘“'s profile picture
Adams Pro ๐• ๐Ÿ‘จโ€๐Ÿ’ป๐Ÿ‘“1 year ago

Have to check your first tweet

DeepSeek Community ยฎ's profile picture
DeepSeek Community ยฎ1 year ago

This was the first post (tweet) I found from the DeepSeek profile, and no one could have imagined at the time that this company would take off like a rocket ๐Ÿš€ and surpass the world's leading AI models. Great job, team! ๐Ÿ‘

matt's profile picture
matt1 year ago

@FlippingProfits they really fw u huh

RIckk's profile picture
RIckk1 year ago

DreamCraft3D FTWpVA3wPBBCD8Vdr8Vshfhow7BvVE7sPmqFKu7Wpump

Sophisticated_Brat's profile picture
Sophisticated_Brat1 year ago

Damnnnn

ram4nd's profile picture
ram4nd1 year ago

This is crazy

Catherine Li's profile picture
Catherine Li1 year ago

ๅ…‰้€Ÿ VS. ๅฎ‡ๅฎ™่†จ่ƒ€็š„้€Ÿๅบฆ<1

Mozzie.'s profile picture
Mozzie.1 year ago

Feel like being the whales stomach

ShadowFates ๐Ÿฆ's profile picture
ShadowFates ๐Ÿฆ1 year ago

where we go, where this legendary A.I gets Started

Related Videos

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior paper page: present DreamCraft3D, a hierarchical 3D content generation method that produces high-fidelity and coherent 3D objects. We tackle the problem by leveraging a 2D reference image to guide the stages of geometry sculpting and texture boosting. A central focus of this work is to address the consistency issue that existing works encounter. To sculpt geometries that render coherently, we perform score distillation sampling via a view-dependent diffusion model. This 3D prior, alongside several training strategies, prioritizes the geometry consistency but compromises the texture fidelity. We further propose Bootstrapped Score Distillation to specifically boost the texture. We train a personalized diffusion model, Dreambooth, on the augmented renderings of the scene, imbuing it with 3D knowledge of the scene being optimized. The score distillation from this 3D-aware diffusion prior provides view-consistent guidance for the scene. Notably, through an alternating optimization of the diffusion prior and 3D scene representation, we achieve mutually reinforcing improvements: the optimized 3D scene aids in training the scene-specific diffusion model, which offers increasingly view-consistent guidance for 3D optimization. The optimization is thus bootstrapped and leads to substantial texture boosting. With tailored 3D priors throughout the hierarchical generation, DreamCraft3D generates coherent 3D objects with photorealistic renderings, advancing the state-of-the-art in 3D content generation.

AK

161,530 views โ€ข 2 years ago