$ account zju3dv
EasyMocap is a multi-view 3D human motion capture toolbox designed for research and prototyping. It provides end-to-end pipelines from video input to 3D body mesh recovery, including camera calibration, 2D keypoint detection (via OpenPose, HRNet, MediaPipe, YOLO), multi-view association and triangulation, SMPL/SMPL-X body model fitting, and neural body rendering. The architecture is modular: a config-driven factory pattern (via YAML and `load_object`) instantiates pipeline stages (detection, triangulation, fitting, visualization), and a command-line entry point `emc` orchestrates the workflow. The repository also contains annotation tools, a real-time 3D visualization server using Open3D, and neural body research code (NeRF-based) for novel view synthesis. Despite its research character, the core pipeline is structured as a reusable application framework with separate packages for estimators, operations, and visualization. However, the codebase exhibits significant technical debt: hardcoded paths, duplicated modules (e.g., two HRNet implementations), incomplete error handling, mixed Chinese/English comments, and stale vendored dependencies (Eigen 3.3.7, pybind11). There are no unit tests, and many scripts rely on external model checkpoints that may not be accessible. The repository is actively maintained with recent commits, but the code quality reflects a fast-moving research project rather than a production-grade system.
Scal3R is a research codebase for CVPR 2026 Highlight paper on large-scale 3D reconstruction from unordered images using test-time training. The core contribution is a novel bidirectional attention mechanism with fast weight updates (TTT layers) that adapts during inference to improve reconstruction quality for large scenes. The repository provides an end-to-end inference pipeline: given a folder of images, it estimates camera poses, depth maps, and produces a colored point cloud. The architecture builds on a DINOv2 backbone and VGGT-based aggregator with custom attention heads, loop detection via SALAD, and pose graph optimization with submap management. The codebase is well-structured with separate modules for data loading, model definition, inference orchestration, and visualization tools. It includes fallback implementations for key components (e.g., Python-only loop solver, simple correlation-based loop detector) to improve portability, though GPU and CUDA are assumed. The repository is primarily a research artifact with clean utilities that could be extracted for other 3D vision projects. Evaluation code and dataset scripts are explicitly marked as not yet released, limiting reproducibility until those are provided.
This repository is a research fork of Meta's Habitat-Sim, extended with 3D Gaussian Splatting (3DGS) for photo-realistic rendering in embodied AI navigation tasks. It provides a full simulation platform with physics (Bullet), sensors (RGB, depth, semantic, fisheye), navigation meshes, and a CUDA-accelerated Gaussian splatting rasterizer supporting dynamic avatars. The codebase includes training and evaluation pipelines for PointNav, ImageNav, ObjectNav, Vision-Language Navigation (StreamVLN, Uni-NaVid), and dynamic avatar avoidance. It also contains an LLM-driven agent system (HabitatAgent) with a bridge API, MCP server, and TUI for interactive navigation. The repository is hybrid: primarily a research platform for embodied AI experiments, but also includes application-like components such as web tools (navmesh editor, object annotation helper), a real-time Rerun viewer, and a conda packaging system. The core C++ simulator is well-architected with managed object patterns, replay recording, and PBR rendering, while the Python layer provides episode generation, prompt-based agent control, and analytics dashboards. Data assets (GS scenes, avatars, checkpoints) are hosted externally on Hugging Face, and the setup requires multiple conda environments for different tasks.