GeometryCrafter
Generate 3D geometry and point clouds from a video
ARC mainly focuses on areas of computer vision, speech, and natural language processing, including speech/video generation, enhancement, retrieval, understanding, AutoML, etc. Considering research developments and industry trends, ARC consistently pursues exploration, innovation, and breakthroughs in technologies.
Player-1: Learning to Play from Synthetic Experience
Multics: Generative Multi-Player World Model with Hierarchical Communication
Generate 3D geometry and point clouds from a video
Steer a 3D camera path through any still image
ColorFlow: Retrieval-Augmented Image Sequence Colorization
4D Shape Generation, CVPRโ2026
Generate stylized photos of a person from your images
Create a 3D model from an image in 10 seconds!
High-fidelity pixel-aligned image-to-3D generation.
High-fidelity pixel-aligned image-to-3D generation.
Autoregressive Long Video Diffusion in Real Time
IC-Custom is designed for diverse image customization.
Edit images using instructions or masks
Generate personalized realistic photos of a person from images
Create custom videos from text and keyframe images
Generate personalized portraits of a specific person from photos
Reconstruct 3D Gaussians from unposes images.
Gradio Demo of DI-PCG
Generate a video of new viewpoints from a few input photos
A 3.2B MMDiT Model distilled from flux-dev
Create interactive videos from images with drag-and-draw controls