mosamdabhi

3dlfm

Official codebase for 3D-LFM paper. Accepted at CVPR, 2024.

MBW

This work generates 2D and 3D landmark labels from videos with only two or three uncalibrated, handheld cameras moving in the wild. NeurIPS 2022.

MBW-Data

svm-voice-recognition

SVM classifier for voice recognition.

neural-shape-prior

PyTorch Implementation for the paper "High Fidelity 3D Reconstructions with Limited Physical Views". 3DV 2021.

mosamdabhi.github.io

https://mosamdabhi.github.io

BayesFlow

A library for constructing specialized neural networks for Bayesian parameter inference (invertible networks) and Bayesian model selection (evidential networks).

clean-fid

PyTorch - FID calculation with proper image resizing and quantization steps [CVPR 2022]

cmu-vision.github.io

coming-soon

A Simple yet Modern Coming Soon HTML Template (Single File)

deep-high-resolution-net.pytorch

The project is an official implementation of our CVPR2019 paper "Deep High-Resolution Representation Learning for Human Pose Estimation"

dreamcoder

dreamgaussian4d

[arXiv 2023] DreamGaussian4D: Generative 4D Gaussian Splatting

esm_meta_protein

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

github-markdown-toc

Easy TOC creation for GitHub README.md

GPTs

leaked prompts of GPTs

jekyll_webpage

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning: LLaVA (Large Language-and-Vision Assistant) built towards GPT-4V level capabilities.

ML_Causal_Class

Machine Learning and Causal Inference taught by Brigham Frandsen

mmselfsup

OpenMMLab Self-Supervised Learning Toolbox and Benchmark

physically-disentangled-representations

Physically Disentangled Representations

project_koala

rmbrualla.github.io

:triangular_ruler: Jekyll theme for building a personal site, blog, project documentation, or portfolio.

screenshot-to-code

Drop in a screenshot and convert it to clean code (HTML/Tailwind/React/Vue)

stable-diffusion

A latent text-to-image diffusion model

stable-dreamfusion

A pytorch implementation of text-to-3D dreamfusion, powered by stable diffusion.

sync_videos

syncstart

Calculate the cut needed at start to sync two media files

theseus

A library for differentiable nonlinear optimization

vissl

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.