AI & Machine Learning Tools

About this collection

AI & Machine Learning Tools is a focused collection within Media Tools, with 37 curated resources.

Resources (showing 1–24 of 37)

• Ad Insertion Sample (GitHub)The ad-insertion reference pipeline shows how to integrate various media building blocks, with analytics powered by the OpenVINO™ Toolkit,…
• AI-Youtube-Shorts-GeneratorLLM-driven highlight detection with Whisper transcription and automatic vertical cropping to turn long videos into shorts, MIT-licensed wit…
• An Overview of the JPEG AI Learning-Based Image Coding StandardIEEE overview paper describing JPEG AI's architecture and coding tools, the first standardized end-to-end learned codec.
• Audio TranscriberTranscodes audio & video files to text, supports MP3, M4A, WAV, MP4, MKV, AVI, MPG & MPEG. No Online API's. Python 3
• Bitrate Ladder Construction via Transfer Learning and Spatio-Temporal FeaturesML-based bitrate ladder optimization achieving 94.1% complexity reduction at only 1.71% BD-rate cost using transfer learning.
• CompressAI-Vision — Video Coding for Machines evaluation platformFramework to design and benchmark video-coding-for-machines pipelines, comparing learned codecs against VTM/HM/JM anchors with MPEG FCM sup…
• CosmoEdgeProduction-oriented Apache-2.0 C++ edge video AI engine that turns RTSP streams and CV/VLM models into visually orchestrated analytics work…
• Deep Reinforced Bitrate Ladders (DeepLadder)NOSSDAV 2021 paper on deep-reinforcement-learning-based bitrate ladder construction for adaptive streaming.
• DQ-Ladder: Deep Q-Network Time/Quality-Aware Bitrate LadderDeep reinforcement learning (DQN) approach to bitrate ladder construction achieving 10.3%+ BD-rate gain and 22% decode-time reduction.
• Efficient Bitrate Ladder Construction for Content-Optimized Adaptive StreamingAcademic paper (Katsenou et al.) using ML to predict Pareto-optimal bitrate ladders from spatio-temporal content features.
• FGVC[ECCV 2020] Flow-edge Guided Video Completion.
• FILM: Frame Interpolation for Large MotionGoogle Research's unified neural network for video frame interpolation handling large motion without requiring optical flow or depth estima…
• FlashVSRCVPR 2026 real-time diffusion-based streaming video super-resolution using one-step, locality-constrained sparse attention with a tiny cond…
• Fraunhofer NNCodec — MPEG Neural Network Coding Reference ImplementationOpen implementation of ISO/IEC 15938-17 (MPEG NNC) for compressing neural networks, conformant as of the 2.0 beta.
• genai-video-super-resolutionAWS sample pipeline combining Real-ESRGAN and SwinIR to upscale low-resolution video up to 4x using AWS services.
• InternVideo — Video Foundation Model FamilyProject page for the InternVideo video foundation models providing CLIP-style video/text embeddings for retrieval and understanding, spanni…
• JukeboxCode for the paper "Jukebox: A Generative Model for Music"
• Mago StudioAn open-source desktop video editor for long-form AI video production. It drives ComfyUI locally so generation runs on the user's own GPU w…
• MoMoAAAI 2025 "Disentangled Motion Modeling for Video Frame Interpolation," diffusion-based motion disentanglement approach.
• mpv-AnimeJaNai — real-time ML upscaling in mpvReal-time 1080p to 4K upscaling inside mpv using compact Real-ESRGAN ONNX models via TensorRT/DirectML and VapourSynth.
• NVIDIA Maxine VFX SDK SamplesAI-powered real-time video effects (denoise, super-res, artifact removal) via Tensor Cores.
• ProPainterICCV 2023 video inpainting tool for object removal/completion using propagation and transformer-based approach, CLI-usable.
• PyNvVideoCodec API Programming GuideNVIDIA's Python bindings over the Video Codec SDK for GPU-accelerated decode/encode pipelines feeding ML and analytics workloads.
• PyTorch Blog: TorchCodec — Easy and Efficient Video DecodingOfficial launch post explaining TorchCodec's design, seeking/indexing model, GPU decode tradeoffs and benchmarks against prior PyTorch medi…