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.
CARI4D is the official CVPR 2026 research codebase for category-agnostic 4D reconstruction of human-object interaction from monocular video. It is fundamentally a research pipeline rather than a production application: raw RGB-D video (primarily BEHAVE, plus HODome/InterCap and custom clips) is processed through a chain of external foundation models - UniDepth for metric depth, NLF/SAM3D for human pose, FoundationPose for object tracking - then aligned, rendered into H5 training files, refined by a learned temporal transformer (CoCoNet), and finally optimized at test time to output temporally consistent SMPL-H body parameters, object 6D pose, and hand contact labels. The repo contains training, inference, preprocessing, and evaluation entry points, but no API/service layer; the runnable scripts are research pipeline drivers.
GS-SDF is a research prototype from HKU-MARS that fuses LiDAR-augmented 3D Gaussian Splatting with a neural Signed Distance Field (SDF) for photorealistic rendering and high-fidelity surface reconstruction. The system ingests data from multiple sensor modalities (LiDAR, RGB-D, stereo) via a modular data parser hierarchy supporting Replica, FAST-LIVO2, KITTI, COLMAP, Oxford Spires, and other formats. It trains a neural SDF field with eikonal and curvature regularization, then initializes and refines 3D Gaussians guided by the SDF to produce view-dependent color and geometry. The pipeline includes real-time ROS visualization (RVIZ), offline mesh extraction via a custom CUDA marching cubes implementation, and evaluation scripts for image metrics (PSNR, SSIM, LPIPS) and structural metrics (Chamfer distance, F-score). The codebase is pre-release, with many TODOs and commented-out code, but exhibits strong modularity in its data loaders, loss functions, optimizer utilities, and coordinate transformations. While primarily a research codebase, it includes application-like features such as a ROS node with interactive keyboard commands and headless rendering modes.
GraphDreamer is a PyTorch-based system for generating compositional 3D scenes from scene graphs. It implements a coarse-to-fine approach where objects are represented as implicit signed distance functions (SDFs) and optimized using gradient signals from 2D diffusion models (DeepFloyd IF for coarse stage, Stable Diffusion for refinement). The system takes text prompts describing objects and their relationships, constructs a scene graph, and generates 3D meshes representing the composed scene. Architecture follows the threestudio framework with modular components for data handling, geometry, materials, guidance, rendering, and system orchestration. Key entry points are in launch.py which supports training, validation, testing, and export modes via command-line interface.
UniTEX is a research-focused repository implementing a two-stage framework for high-fidelity 3D texture generation from arbitrary 3D shapes. Stage 1 uses LoRA-adapted Diffusion Transformers for multi-view texture synthesis, while Stage 2 employs a transformer-based Large Texturing Model (LTM) to predict Texture Functions in unified 3D space, bypassing UV mapping limitations. The repository integrates super-resolution (TSD_SR) for detail enhancement and provides tools for mesh processing, rendering, and texture reprojection. It includes training scripts, model architectures, and utility libraries, indicating its primary purpose is to support experimentation and reproduction of the CVPR 2026 paper's methodology rather than serving as a standalone end-user application.
This repository is a curated awesome-list of research papers, projects, datasets, and industry demos related to digital humans: 3D avatar generation and animation, clothed human reconstruction, head avatars, human motion generation, virtual try-on, cloth simulation, and related topics. It contains only a README.md plus LICENSE; there is no application code, no executable pipeline, no tests, no CI, and no dependency manifests. Despite the data_research classification, it is best understood as a manually maintained literature index rather than a data pipeline or software project.