Sparse Voxels Rasterization: Real-Time High-Fidelity Radiance Field Rendering(svraster.github.io)

103 points by jasondavies 1 year ago | 18 comments

EfficientSAM(yformer.github.io)

47 points by Thomashuet 2 years ago | 7 comments

Neuralangelo: High-Fidelity Neural Surface Reconstruction(research.nvidia.com)

74 points by bx376 3 years ago | 11 comments

CosAE: Learnable Fourier Series for Image Restoration(sifeiliu.net)

50 points by E-Reverance 1 year ago | 13 comments

MeshAnything – Converts 3D representations into efficient 3D meshes(buaacyw.github.io)

277 points by flockonus 2 years ago | 62 comments

GaussianObject: Just Taking Four Images to Get a High-Quality 3D Object(gaussianobject.github.io)

140 points by smusamashah 2 years ago | 17 comments

Visual Anagrams: Generating optical illusions with diffusion models(dangeng.github.io)

758 points by beefman 2 years ago | 64 comments

Project page for Visual Anagrams, a University of Michigan research paper using pretrained diffusion models to generate multi-view optical illusions.

Diffusion for World Modeling(diamond-wm.github.io)

455 points by francoisfleuret 2 years ago | 207 comments

Project page for DIAMOND, a NeurIPS 2024 spotlight paper on using diffusion models as world models for reinforcement learning agents in Atari games.

MIT 6.S184: Introduction to Flow Matching and Diffusion Models(diffusion.csail.mit.edu)

362 points by __rito__ 1 year ago | 21 comments

Course page for MIT 6.S184, an introduction to flow matching and diffusion models built from stochastic differential equations, with notes, lectures, and labs.

Diffusion models are real-time game engines(gamengen.github.io)

1087 points by jmorgan 2 years ago | 391 comments

Project page for GameNGen, a Google Research paper showing a diffusion model running a playable game in real time, with links to the paper, arXiv, and a demo video.

TurboQuant: Redefining AI efficiency with extreme compression(research.google)

495 points by ray__ 7 months ago | 134 comments

Google Research blog post introducing TurboQuant, a method for extreme compression to improve AI model efficiency.

RubyLLM: A Ruby framework for all major AI providers(rubyllm.com)

439 points by doener 4 months ago | 75 comments

Documentation homepage for RubyLLM, an open-source Ruby framework offering a unified API across major AI providers for chatbots, agents, and RAG apps.