Anand K Subramanian

openpaper. Open Paper is a workbench for managing your research library. Read, annotate, and understand your papers all in one place. Use an AI assistant to conduct your literature review.

vgg-ttt. [CVPR'26] Official code for the paper "VGG-T³: Offline Feed-Forward 3D Reconstruction at Scale"

TTT3R. [ICLR 2026] A simple state update rule to enhance length generalization for CUT3R

ml-aim. This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.

OC_SORT. [CVPR2023] The official repo for OC-SORT: Observation-Centric SORT on video Multi-Object Tracking. OC-SORT is simple, online and robust to occlusion/non-linear motion.

hallmark. Anti-AI-slop design skill for Claude Code, Cursor, and Codex.

YOLO. An MIT License of YOLOv9, YOLOv7, YOLO-RD

Optimal-Flow-Matching. The official repository for the paper "Optimal Flow Matching: Learning Straight Trajectories in Just One Step" (NeurIPS 2024)

ncnn. ncnn is a high-performance neural network inference framework optimized for the mobile platform

uncompressed. My arr stack. Hardened Docker Compose config for Jellyfin + Sonarr/Radarr + qBittorrent with VPN namespace isolation and zero-trust ingress.

TurboReg. [ICCV-2025] TurboReg: TurboClique for Robust and Efficient Point Cloud Registration

pytorch_volumetric. Volumetric structures such as voxels and SDFs implemented in pytorch

pydags. Simple, lightweight, extensible DAG framework for Python with a Kubeflow-like API

amd-strix-halo-toolboxes. Python

madpose. [CVPR 2025 Highlight] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affine Corrections of Monocular Depth Priors"

MILo_rtx50. Build a version works on cuda 12.x with RTX 50 series GPU. [SIGGRAPH Asia 2025 - TOG] Official implementation of MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction

latex-docker. A set of lightweight Docker images for building LaTeX documents

torch-spherical-harmonics. Real Spherical Harmonics for PyTorch

taichi-splatting. Python

deep-image-matching. Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM software. Supports high-resolution formats and images with rotations. Both CLI and GUI are supported.

vision.cpp. Computer Vision ML inference in C++

panst3r. PanSt3R: Multi-view Consistent Panoptic Segmentation (official code)

pyroutelib3. Simple routing over OpenStreetMap data

Low-Cost-Mocap. Low cost motion capture system for room scale tracking

CImg. The CImg Library is a small and open-source C++ toolkit for image processing

tiny-differentiable-simulator. Tiny Differentiable Simulator is a header-only C++ and CUDA physics library for reinforcement learning and robotics with zero dependencies.

drjit. Dr.Jit — A Just-In-Time-Compiler for Differentiable Rendering

stable-diffusion.cpp. Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

fourier-draw. Draw any shape from an image by Fourier transform using only Matplotlib.

vit.cpp. Inference Vision Transformer (ViT) in plain C/C++ with ggml

Egaroucid. Super Strong and Fast Othello AI / Computer Othello Reversi

demucs. Code for the paper Hybrid Spectrogram and Waveform Source Separation

beta-splatting. [SIGGRAPH'25] Official implementation for the paper "Deformable Beta Splatting"

taichi_3d_gaussian_splatting. An unofficial implementation of paper 3D Gaussian Splatting for Real-Time Radiance Field Rendering by taichi lang.

pytorch-face-reaging-network. PyTorch Lightning implementation of Disney's face re-aging network (FRAN) paper.

Qwen3-Coder. Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.

crictty. cricket scores in the terminal

tinyengine. [NeurIPS 2020] MCUNet: Tiny Deep Learning on IoT Devices; [NeurIPS 2021] MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning; [NeurIPS 2022] MCUNetV3: On-Device Training Under 256KB Memory

fluentui-system-icons. Fluent System Icons are a collection of familiar, friendly and modern icons from Microsoft.

EasyGaussianSplatting. Python

tinysplat. A minimal 3D Gaussian splatting implementation with depth and density regularization

claycode. Shape-Free scannable visual codes

torch-splatting. A pure pytorch implementation of 3D gaussian Splatting

supersplat. 3D Gaussian Splat Editor

3dgs-warp-scratch. Build 3D Gaussian Splatting from scratch with NVIDIA Warp in Python — CPU/GPU compatible, with a clean and minimalist design focused on learning modern graphics.

conditional-flow-matching. TorchCFM: a Conditional Flow Matching library

FramePack. Lets make video diffusion practical!

loco-mujoco. Imitation learning benchmark focusing on complex locomotion tasks using MuJoCo.

VideoPainter. [SIGGRAPH2025] Official repo for paper "Any-length Video Inpainting and Editing with Plug-and-Play Context Control"

flow_matching. A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

talk-to-ai. Talk To AI with FastRTC enables natural, real-time voice conversations with AI using WebRTC, offering customizable voices, interfaces, and local or cloud-based API integration.

AWML. Python

stockfish. Integrates the Stockfish chess engine with Python

fastrtc. The python library for real-time communication

image-matching. Superpoint and Superglue training and testing code, also some traditional method (SIFT and ORB)

openMVS. open Multi-View Stereo reconstruction library

pyBregMan. Python

x-flux-comfyui. Python

PyPOTS. A Python toolkit/library for reality-centric machine/deep learning & data mining on partially-observed time series, with 50+ SOTA neural network models for scientific analysis tasks (imputation, classification, clustering, forecasting, anomaly detection, cleaning) on incomplete industrial irregularly-sampled multivariate TS with NaN missing values

Feature-Distillation. Python

rsl_rl. A fast and simple implementation of learning algorithms for robotics.

MobileSAM-pytorch. Reproduction of MobileSAM using pytorch

RPI-ZERO-2-OnnxStream. Running Stable Diffusion on a RPI Zero 2 (or in 260MB of RAM)

MobileSAM. This is the official code for MobileSAM project that makes SAM lightweight for mobile applications and beyond!

jetson-intro-to-distillation. A tutorial introducing knowledge distillation as an optimization technique for deployment on NVIDIA Jetson

Infusion. Official implementation for paper: InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior

HunyuanVideo. HunyuanVideo: A Systematic Framework For Large Video Generation Model

TensorNVMe. A Python library transfers PyTorch tensors between CPU and NVMe

face-swap. Face Swap Finetuned Model

MeshAnything. [ICLR 2025] From anything to mesh like human artists. Official impl. of "MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers"

pytorch_HMR. pytorch version of "End-to-end Recovery of Human Shape and Pose"

D3DP. [ICCV2023] The PyTorch implementation for "Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation"

gaussian-splatting-web. TypeScript

opendr. A modular, open and non-proprietary toolkit for core robotic functionalities by harnessing deep learning

diff-gaussian-rasterization. Cuda

Michelangelo. [NeurIPS 2023] Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

loras-dev. An AI image generator w/ Flux LoRAs

async_torchwindow. An async window to visualize an Image tensor or a Gaussian Splatting scene

100Days. GPU Kernels

Open3D-PoissonRecon. Poisson Surface Reconstruction

Hunyuan3D-2. High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

CraftsMan3D. CraftsMan: High-fidelity Mesh Generation with 3D Native Diffusion and Interactive Geometry Refiner

build-your-own-x. Master programming by recreating your favorite technologies from scratch.

arttime. arttime is a CLI application that blends beauty of ASCII / text art with functionality of clock / timer / pattern-based time manager in terminal ⏰

homies. home dir & package management

PointCloudToolBox. Point cloud processing tool library.

APMA_2070_ENGN_2912_SPRING_2024. Jupyter Notebook

deepxde. A library for scientific machine learning and physics-informed learning

neuraluq. Python

neuraloperator. Learning in infinite dimension with neural operators.

fastmath. Go

zuho. WebGL equirectangular image viewer with many projection method.

tensorneat. GPU-accelerated NeuroEvolution of Augmenting Topologies (NEAT)

whisperX. WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

genesis-world. Simulation platform for general-purpose robotics & embodied AI learning.

markitdown. Python tool for converting files and office documents to Markdown.

PDFMathTranslate. [EMNLP 2025 Demo] PDF scientific paper translation with preserved formats - 基于 AI 完整保留排版的 PDF 文档全文双语翻译，支持 Google/DeepL/Ollama/OpenAI 等服务，提供 CLI/GUI/MCP/Docker/Zotero

TRELLIS. Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

awesome-falsehood. 😱 Falsehoods Programmers Believe in

n-sphere-pytorch. Efficient pytorch transformation function between cartesian and spherical coordinates in n-dimensions.

Parallel-Computing-Cuda-C. CUDA Learning guide

OmniCV-Lib. A computer vision library for omnidirectional (360 degree) cameras.

scientifica. tall, condensed, bitmap font for geeks

SAM. Official Implementation for "Only a Matter of Style: Age Transformation Using a Style-Based Regression Model" (SIGGRAPH 2021) https://arxiv.org/abs/2102.02754

coconut_cvpr2024. Jupyter Notebook

coco. Numerical Black-Box Optimization Benchmarking Framework

libvh. Cuda

cinolib. A generic programming header only C++ library for processing polygonal and polyhedral meshes

robust-laplacians-py. Build high-quality Laplace matrices on meshes and point clouds in Python. Implements [Sharp & Crane SGP 2020].

Algotype.js. A JavaScript library for easier typesetting of algorithms in HTML pages.

PhysariumCubeMap. Physarium on CubeMap using CUDA for simulation

piglot. A package for the optimisation of numerical responses

yazi. 💥 Blazing fast terminal file manager written in Rust, based on async I/O.

ComfyUI_ProPainter_Nodes. 🖌️ ComfyUI implementation of ProPainter framework for video inpainting.

fatkernels. Collection of fat kernels for deep learning writen in triton

practice-triton. 삼각형의 실전! Triton

TritonPractices. Some Kernels for practising Triton.

annotated-mamba. Annotated version of the Mamba paper

Triton-Puzzles. Puzzles for learning Triton

executorch. On-device AI across mobile, embedded and edge for PyTorch

open-webui. User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

SecureAI-Tools. Private and secure AI tools for everyone's productivity.

DUP-ocropy. Python-based tools for document analysis and OCR

pypdf. A pure-python PDF library capable of splitting, merging, cropping, and transforming the pages of PDF files

poetical_computer_vision. 31 metamophoses of Ada Lovelace, made with code

LLM-Engineers-Handbook. The LLM's practical guide: From the fundamentals to deploying advanced LLM and RAG apps to AWS using LLMOps best practices

nnabla. Neural Network Libraries

sliders. Concept Sliders for Precise Control of Diffusion Models

ComfyUI_examples. Examples of ComfyUI workflows

comfyui-colab. comfyui colabs templates new nodes

smalldiffusion. Simple and readable code for training and sampling from diffusion models

planify. Task manager with Todoist, Nextcloud & CalDAV support designed for GNOME

pycuda. CUDA integration for Python, plus shiny features

torchdiffeq. Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

pytorch-forecasting. Time series forecasting with PyTorch

tslearn. The machine learning toolkit for time series analysis in Python

MIDA-pytorch. PyTorch implementation of "MIDA: Multiple Imputation using Denoising Autoencoders"

Time-Series-Library. A Library for Advanced Deep Time Series Models for General Time Series Analysis.

laion-icons. Filtering simple icons from LAION

burn. Burn is a next generation tensor library and Deep Learning Framework that doesn't compromise on flexibility, efficiency and portability.

shumai. Fast Differentiable Tensor Library in JavaScript and TypeScript with Bun + Flashlight

MotoricaDanceDataset. Python

finetrainers. Scalable and memory-optimized training of diffusion models

GAN_stability. Code for paper "Which Training Methods for GANs do actually Converge? (ICML 2018)"

fpsample. Python efficient farthest point sampling (FPS) library. Compatible with numpy.

potree. WebGL point cloud viewer for large datasets

ml-depth-pro. Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

city-roads. Visualization of all roads within any city

City-Maps-Poster-Generator. Creates beautiful posters from stylized arial views of cities or other places on earth

circle-tiling. Variations on the surface tiling

Ofelia. A real-time cross-platform creative coding tool for multimedia development

Circlism. Digital Circlism using algorithms

prettymaps. Draw pretty maps from OpenStreetMap data! Built with osmnx +matplotlib + shapely

generativeart. Generative Art in Go

circle-city-maps. Circle Maps of cities in various styles

latex-resources. Collection of LaTeX resources and examples.

sdf. Parallelized triangle mesh --> continuous signed distance field on CPU

falling-sand-game. Falling sand game in cellular automata style.

LayerDiffuse_DiffusersCLI. LayerDiffuse in pure diffusers without any GUI

IC-Light. More relighting!

kernl. Kernl lets you run PyTorch transformer models several times faster on GPU with a single line of code, and is designed to be easily hackable.

LightZero. [NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)

SDXLWorkflow. OUTDATED SDXL workflows for ComfyUI

potpourri3d. An invigorating blend of 3D geometry tools in Python.

aiconfig. AIConfig is a config-based framework to build generative AI applications.

langchain-tutorials. A set of LangChain Tutorials from my youtube channel

QGIS. QGIS is a free, open source, cross platform (lin/win/mac) geographical information system (GIS)

awesome-gis. 😎Awesome GIS is a collection of geospatial related sources, including cartographic tools, geoanalysis tools, developer tools, data, conference & communities, news, massive open online course, some amazing map sites, and more.

lectures. Material for gpu-mode lectures

LeanRL. LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.

color-matcher. automatic color-grading and image data augmentation

ExAvatar_RELEASE. Official PyTorch implementation of "Expressive Whole-Body 3D Gaussian Avatar", ECCV 2024.

NEAT-JAX. An implementation of Neuroevolution of Augmented Topologies Algorithm compatible with EvoJAX. Made to play Neural Slime Volleyball

felafax. Felafax is building AI infra for non-NVIDIA GPUs

python-typesetting. A Python library letting you invoke TeX-inspired typesetting algorithms

htbuilder. A purely-functional HTML builder for Python. Think JSX rather than templates.

compone. Component framework for Python

3d_scene_segmentation. scene segmentation using blender

clipboard.js. :scissors: Modern copy to clipboard. No Flash. Just 3kb gzipped :clipboard:

q5xjs. A small and fast alternative (experimental) implementation of p5.js

mistletoe. A fast, extensible and spec-compliant Markdown parser in pure Python.

Temml. TeX-to-MathML conversion library in JavaScript

baudio. Audio Tinkerers Plaything (DAC/CMoy Amp/VU/DigiPots)

pytorch-lasso. L1-regularized least squares with PyTorch

RTF. A State-Space Model with Rational Transfer Function Representation.

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

maxdiffusion. Python

EasyMocap. Make human motion capture easier.

NumKong. SIMD-accelerated distances, dot products, matrix ops, geospatial & geometric kernels for 16 numeric types — from 6-bit floats to 64-bit complex — across x86, Arm, RISC-V, and WASM, with bindings for Python, Rust, C, C++, Swift, JS, and Go 📐

chronofile. Personal time tracking app

leafmap. A Python package for interactive mapping and geospatial analysis with minimal coding in a Jupyter environment

3dpcp_book_codes. Jupyter Notebook

cameractrls. Camera controls for Linux

study-music. An "awesome music theory" kinda wiki with books, resources and courses for studying everything about music and sound

audioFlux. A library for audio and music analysis, feature extraction.

NanoLog. Low Latency C++11 Logging Library

buckaroo. The decentralized package manager for C++ and friends 🏝️

modern-cpp-template. A template for modern C++ projects using CMake, Clang-Format, CI, unit testing and more, with support for downstream inclusion.

pitchfork. Pitchfork is a Set of C++ Project Conventions

Quads. Computer art based on quadtrees.