- Tokyo, Japan
- https://www.kaggle.com/nagadomi
Stars
WebRTC and ORTC implementation for Python using asyncio
Fast and memory-efficient exact attention
Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation
Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding
Neighborhood Attention Extension. Bringing attention to a neighborhood near you!
PyTorch code and models for the DINOv2 self-supervised learning method.
[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation
The simplest, fastest repository for training/finetuning medium-sized GPTs.
A collection of tools for neural compression enthusiasts.
SAM-tak / eeVR
Forked from EternalTrail/eeVRBlender addon for rendering equirectangular and dome projection images using the eevee rendering engine.
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
High Resolution Depth Maps for Stable Diffusion WebUI
Metric depth estimation from a single image
Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"
Face Analysis: Detection, Age Gender Estimation & Recognition
Rembg is a tool to remove images background
The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Python library for working with HEIF images and plugin for Pillow.
[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training
[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer
Simple, safe way to store and distribute tensors
Mixbox is a library for natural color mixing based on real pigments.