PyHessian is a Pytorch library for second-order based analysis and training of Neural Networks

Landscaper is a comprehensive Python framework designed for exploring the loss landscapes of deep learning models.

The interactive graphing library for Python ✨

NeRF from scratch (CS180 project)

Main Web Site (Online Books)

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

TriplaneGaussian: A new hybrid representation for single-view 3D reconstruction.

Optical illusions using stable diffusion

A Code Release for Mip-NeRF 360, Ref-NeRF, and RawNeRF

[CVPR23 Highlight] Implementation for Panoptic Lifting

3D transformations for Python.

Conversion between different conventions of camera matrices and transform matrices.

CamTools: Camera Tools for Computer Vision

Pytorch implementation of Diffusion Models (https://arxiv.org/pdf/2006.11239.pdf)

Tools to Design or Visualize Architecture of Neural Network

[NeurIPS'22] MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

[ECCV'20] Convolutional Occupancy Networks

Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

Animation engine for explanatory math videos

Let us control diffusion models!

A keras project with Weights & Biases integration to achieve complete MLOps maturity for experimentation and model development

A tool for refurbishing and modernizing Python codebases

A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets.

A curated list of awesome neural radiance fields papers

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

Code release for NeRF (Neural Radiance Fields)

NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning

Explanation to key concepts in ML