LingBot-Map

ABot-Recon is a streaming 3D-reconstruction model and inference tool for reconstructing long video streams from video frames alone. At each step, it caches key-value features from the preceding 11 frames, predicts a point map in the current camera coordinate system, estimates the adjacent relative camera pose, and composes those poses sequentially into a global trajectory and point cloud without persistent learned long-range memory. It can output camera poses, relative poses, local and world point maps, colors, confidence maps, and run metadata. An optional loop-closure backend retrieves candidate revisited-frame pairs using DINOv2-SALAD descriptors, predicts relative-pose constraints with ABot-Recon, and refines the trajectory through sparse pose-graph optimization. The repository provides Python and command-line interfaces, a public model checkpoint, a demo, evaluation code, and visualization utilities. The released configuration targets Linux, Python 3.10 or later, PyTorch 2.5.1, and CUDA 12.1; source code is licensed under Apache License 2.0, while the model weights have separate terms in MODEL_LICENSE.md.

LingBot-World 2.0, also called LingBot-World-Infinity, is an AI world-modeling system from the Robbyant Team for generating interactive video environments. Its causal pretraining paradigm is designed for an unbounded interaction horizon, while a distilled real-time variant is claimed to drive 720p video streams at 60 frames per second. The system supports diverse actions, including attacking, archery, spell-casting, and shooting, along with text-driven events. Its agentic harness uses a pilot agent to plan and execute character behavior and a director agent to synthesize new environmental elements as a scene progresses. The causal inference implementation processes video frames chunk by chunk with KV caching rather than processing the entire sequence at once. The release provides inference code and model weights, including a 14B causal-fast model, with a codebase built on Wan2.2; models are distributed through Hugging Face and ModelScope, and the real-time system can be tried through Reactor on the web or LingGuang on mobile. The project is licensed under CC BY-NC-SA 4.0 for non-commercial use. It states that deployment code will not be released and points to SGLang or flashdreams for self-deployment references.

VidMap is an offline structure-from-motion system for video, developed by the Computer Vision and Geometry group (cvg). It combines temporal feature tracks, loop closures, metric depth, and global optimization to estimate camera poses, camera intrinsics, and a sparse 3D map from video or extracted frames. The Python package writes the reconstruction as a COLMAP model and supports optional browser-based HTML visualization and Rerun playback or flythrough recordings. The repository provides setup and execution workflows built around COLMAP, PyCOLMAP, PyTorch, xFormers, and GPU acceleration through CUDA and cuDSS.

FoundationPose is an NVIDIA Research implementation of a unified foundation model for 6D object pose estimation and tracking of novel objects. It supports model-based operation from a CAD model and model-free operation from a small set of reference images, applying to a new object at test time without fine-tuning. A neural implicit representation provides novel-view synthesis while keeping the downstream pose-estimation modules shared across both setups; the system uses large-scale synthetic training, a transformer-based architecture, contrastive learning, and language-model assistance. The repository includes robotic and augmented-reality demos and provides Docker-based setup instructions and downloadable model weights.

LightNav-0 is an open-source generalist embodied-navigation model from the Light Origins Team. It uses a pretrained Qwen3-VL backbone with a single egocentric RGB stream and natural-language instructions to control humanoid, quadruped, wheeled, and aerial robots, transferring across tasks, embodiments, and scenes without per-task or per-benchmark fine-tuning. The model extends the vocabulary with dual-channel pointing tokens and residual vector-quantized action tokens rather than adding navigation-specific prediction heads. At each step, it emits an affordance point representing a feasible local direction or waypoint and an object point representing the goal, followed by three action tokens that decode to ten future SE(2) waypoints for an embodiment-specific low-level controller. Its temporally aware history compressor samples older frames less frequently, pools them more coarsely, and preserves ordering with timestamp tokens while bounding the visual context. The repository includes a released checkpoint and action decoder, command-line prediction, a vLLM-based server with WebSocket streaming, a MuJoCo simulation demo, evaluation harnesses, and a ROS 2 deployment stack with adapters for the Unitree Go2 and LimX TRON 1. The project is released under the Apache License 2.0; the included EVT-Bench is separately licensed CC BY-NC-SA 4.0.