A JavaScript library for generating random user agents with data that's updated daily.

Codebase for reproducing the experiments of the semantic uncertainty paper (short-phrase and sentence-length experiments).

Entropy Based Sampling and Parallel CoT Decoding

tailwindcss-motion is a Tailwind CSS Plugin made at RomboHQ. It’s a simple, yet powerful, animation library with a simple syntax.

A syntax-highlighting pager for git, diff, grep, and blame output

Clean and simple starter repo using the T3 Stack along with Expo React Native

The best way to start a full-stack, typesafe Next.js app

just a bunch of useful embeddings

Franken UI is an HTML-first, open-source library of UI components that works as a standalone or as a Tailwind CSS plugin. It is compatible with UIkit 3. The design is influenced by shadcn/ui.

Trick iOS Into Animating App Icons

Easily add an App Clip for iOS apps built with React Native

An LDraw™ editor for LEGO® style digital building instructions.

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

3D generation on ImageNet [ICLR 2023]

PyTorch implementation of "Improved Modeling of 3D Shapes with Multi-view Depth Maps". 3DV 2020

For Ego4D VQ3D Task

[CVPR 2024] G3DR: Generative 3D Reconstruction in ImageNet

Official implementation of "Fed3DGS: Scalable 3D Gaussian Splatting with Federated Learning"

🌊 [ECCV'24 Oral] MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

A Monocular depth-estimation for in-the-wild AutoFocus application.

Refocus an image just by clicking on it with no additional data

[ECCV2020 Spotlight] Efficient Spatio-Temporal Recurrent Neural Network for Video Deblurring

[ECCV2022] Animation from Blur: Multi-modal Blur Decomposition with Motion Guidance

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Dense Prediction Transformers

This repo contains the projects: 'Virtual Normal', 'DiverseDepth', and '3D Scene Shape'. They aim to solve the monocular depth estimation, 3D scene reconstruction from single image problems.