thehardwarestore.ai

This repository, NVlabs/tiny-cuda-nn, is a high-performance C++/CUDA library and PyTorch extension for training and querying neural networks with a focus on extreme GPU efficiency. It provides a modular, JSON-configurable framework of specialized components: input encodings (multiresolution hash grids, spherical harmonics, frequency, etc.), network architectures (fully fused MLP using Tensor Cores, CUTLASS-based MLP), loss functions, and optimizers (Adam, Shampoo, Novograd, etc.). The library supports runtime JIT compilation to fuse forward, backward, and loss kernels into single CUDA kernels, yielding up to 5x speedups. It is the engine behind NVIDIA's Instant Neural Graphics Primitives (Instant NGP) and is widely used in NeRF and neural rendering research. The codebase is production‑quality, with extensive use of templates, GPU memory arenas, CUDA graphs, multi‑stream parallelism, and comprehensive CI across many CUDA versions and GPU architectures. Although primarily a library, it includes sample applications and benchmarks that demonstrate its use in image overfitting and throughput measurement. PyTorch bindings via pybind11 make it accessible for Python‑based research workflows.

This repository is a curated 'awesome list' for 3D Gaussian Splatting (3DGS) research papers, complemented by a static site generator and a YAML editor. The core functional code reads a YAML database of ~500 papers and generates a single-page HTML site with search, filter by year/tag, and paper selection for sharing. It includes a PyQt6 GUI for managing the YAML file, an arXiv integration module to fetch metadata, a PDF thumbnail generator, and a link checker for CI. The frontend uses vanilla CSS and JS with no framework. The codebase is well-organized for its purpose but lacks deep abstraction; the template engine is a thin wrapper around string.Template, and the editor is tightly coupled to the application. The main value is the curated paper list itself rather than the software engineering.

This repository is a curated list of research papers and resources on editing techniques for Neural Radiance Fields (NeRF) and 3D Gaussian Splatting. It contains hundreds of entries organized by year and venue, covering seminal works, surveys, and recent advances in 3D scene editing, stylization, inpainting, relighting, and more. The repository is maintained by Weize Li and collaborators from multiple institutions. It serves as a comprehensive index for researchers and practitioners, but contains no executable code, libraries, or data pipelines. It is purely a reference list.

LiveTalking is a real-time interactive streaming digital human engine that synchronizes lip movements with audio generated from text or speech input. It functions as a production-grade web server (Flask + aiohttp) supporting WebRTC, RTMP, and virtual camera output, enabling applications like live streaming, virtual assistants, and conversational avatars. The system integrates a pluggable pipeline: user input → optional LLM (OpenAI-compatible) → TTS (8+ providers including EdgeTTS, CosyVoice, GPT-SoVITS) → lip-sync model inference (Wav2Lip, MuseTalk, Ultralight Digital Human) → video frame compositing → streaming output. It also includes ASR via a local FunASR/SenseVoice WebSocket server and a web admin UI for session management and avatar generation. Architecturally, it follows a plugin-based design using a decorator registry (registry.py) that allows extending TTS, Avatar, and Output modules via registration. The core rendering loop in BaseAvatar manages three concurrent threads (TTS, inference, frame processing) with queue-based data flow. WebRTC integration uses aiortc for peer connections, and the system supports multi-session concurrency with session limits. While primarily an application, it embeds research-derived model code (Whisper, face detection, face parsing) and includes a benchmark script for ASR latency comparison. The codebase has some technical debt: duplicated face detection utilities, stale Dockerfile (Python 3.10/torch 1.12 vs README's newer requirements), and commented-out legacy code. However, the core architecture is solid, and the plugin system and audio utilities are well-crafted and reusable.

This repository implements Pixie, a research framework for predicting dense physical material fields (density, Young's modulus, Poisson's ratio, material ID) from 2D image observations of 3D objects. Hydra configs drive a multi-stage pipeline: Objaverse object retrieval, Blender rendering, NeRF-based CLIP feature field training (F3RM), Gaussian Splatting training, voxel grid feature extraction, VLM-based or neural material segmentation, and MPM physics simulation via the vendored PhysGaussian codebase. The pipeline.py entry point orchestrates these stages with caching and reproducibility checks, while render.py produces Blender visualizations of segmented physics fields. Real-scene mode extends the same pipeline to captured datasets using COLMAP dataparsers. The repository also contains the full PixieVerse data curation workflow: class-based Objaverse selection using sentence-transformers, large-scale parallel Blender rendering, VLM-based filtering and critique (Gemini/Claude/GPT/Qwen via the vendored vlmx agent framework), and Streamlit tools for human-in-the-loop label correction and simulation validation. The discrete (semantic segmentation) and continuous (property regression) 3D UNet training lives in the vendored Wavelet-Generation submodule, with shared utilities in pixie/training_utils.py and normalization statistics already computed in normalization_stats/. Architecturally this is a hybrid research/application repository: primarily a configuration-driven pipeline framework with CLI entry points, but also a dataset-generation and model-training workflow. It depends heavily on vendored third-party code (nerfstudio, f3rm, PhysGaussian, Wavelet-Generation, vlmx) and shells out to Blender, CUDA rasterizers, and Hugging Face. Quality is research-grade: disciplined Hydra configs, contextual config snapshots, and skip-if-exists caching coexist with hardcoded user-specific paths, commented-out dead code, and a subprocess-heavy orchestration style. Download scripts for pre-trained models and the PixieVerse dataset are included and functional.