SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.

Demo code for "A Unified Differentiable Boolean Operator with Fuzzy Logic" (SIGGRAPH 2024)

[ECCV24] MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos

The easy way to send notifications

Python logging made (stupidly) simple

These scripts are used to download RealEstate10K dataset.

The KittyCAD modeling app.

Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

Implementation of Lumiere, SOTA text-to-video generation from Google Deepmind, in Pytorch

An open-source impl. of Large Reconstruction Models

Generative Models by Stability AI

Code for "The One Where They Reconstructed 3D Humans and Environments in TV shows" appearing in ECCV 2022.

Code for the paper "pix2gestalt: Amodal Segmentation by Synthesizing Wholes" (CVPR 2024)

Dense Optical Tracking: Connecting the Dots

CoTracker is a model for tracking any point (pixel) on a video.

Uniform Manifold Approximation and Projection

A Blender add-on for importing a sequence of OBJ meshes as frames

DSPy: The framework for programming—not prompting—foundation models

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/

The Replica Dataset v1 as published in https://arxiv.org/abs/1906.05797 .

Memray is a memory profiler for Python

Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification

ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction. NeurIPS 2021.