VidMap

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-Map is a feed-forward 3D foundation model from the Robbyant Team for streaming 3D reconstruction from image sequences and video. Its Geometric Context Transformer unifies coordinate grounding, dense geometric cues, and long-range drift correction through anchor context, a pose-reference window, and trajectory memory. The system uses paged KV-cache attention for streaming inference and supports interactive browser-based reconstruction with point-cloud visualization, keyframe intervals, windowed processing for long sequences, and sky masking. It also provides an offline rendering pipeline for image folders or video, along with evaluation pipelines for datasets including KITTI and Oxford Spires. The repository reports approximately 20 FPS inference at 518×378 resolution on sequences exceeding 10,000 frames, and documents PyTorch installation with FlashInfer as the recommended attention backend and native SDPA as a fallback.

Colite is an experimental C++17 structure-from-motion and multi-view stereo system that reconstructs 3D scenes from overlapping images. Its pipeline performs incremental structure-from-motion with support for multiple models, continuation, and Sim(3) merging; feature extraction and matching; PatchMatch stereo with geometric consistency; stereo fusion; meshing; simplification; and texture-atlas generation. It produces COLMAP-compatible sparse models, RGB and normal dense point clouds, Poisson or Delaunay meshes, and textured OBJ models with MTL and atlas PNG files. CPU and optional CUDA implementations are provided for SIFT, descriptor matching, and PatchMatch Stereo, and resumable stage manifests allow processing to continue from saved stages. The repository describes the current build as alpha-quality, primarily developed and tested on Ubuntu 22.04 and WSL2; native Windows builds are not yet validated as a supported release target.

4DAnyone is an open-source generative AI pipeline from ant-research that converts a casual monocular video of one person into synchronized videos from multiple virtual camera views for downstream 3D or 4D Gaussian-splatting reconstruction. It supports configurable camera layouts, including full 360-degree or frontal-arc coverage, multiple pitch layers, adjustable yaw ranges, and flexible view counts. The repository provides inference scripts, automatically downloadable models and examples, motion-recovery outputs, camera metadata, skeleton videos, and generated target-view videos. Input footage should be at least 720p, preferably 1080p, use a 9:16 portrait aspect ratio, contain a single person in a full-body or upper-body shot, include at least 121 frames, and have only mild camera motion.

Roomform is an open-source pipeline that converts registered indoor point-cloud scans—including laser scans, ARKit exports, and RGB-D reconstructions—into structured, editable scenes. It infers walls and openings, classifies oriented object boxes, associates segmented points with objects, and produces evidence-gated object meshes; the pipeline writes scene JSON, GLB output, per-object meshes, and intermediate grids while streaming NDJSON progress, including a boundary-only partial scene during processing. The package provides point-cloud processing and object-lifting backends, including Point Transformer V3 with local clustering, SpatialLM, and UniDet3D, with optional remote reconstruction through SAM 3D Objects via fal.ai. It includes a read-only debug viewer and an editor for moving objects and saving scenes back to the native format. The code is licensed under Apache 2.0; trained weights and synthetic data, when published, are listed as CC BY-NC 4.0.