visionaix

VisionAIx

GitHub
https://github.com/VisionAIx

visionaix / sam3-1

SAM 3.1 (Segment Anything 3.1): Unified promptable segmentation for images. Supports text, point, and box prompts. Detects and segments 270K+ concepts. By Meta FAIR.

2 runs
Public

visionaix / sam3

SAM 3.1 (Segment Anything 3.1): Unified promptable segmentation for images. Supports text, point, and box prompts. Detects and segments 270K+ concepts. By Meta FAIR.

3 runs
Public

visionaix / metric3dv2

Metric3D v2 (TPAMI 2024): Monocular metric depth and surface normals from a single image. Predicts real-world depth in meters. Works indoor and outdoor.

12 runs
Public

visionaix / metric3d-v2

Metric3D v2 (TPAMI 2024): Monocular metric depth and surface normals from a single image. Predicts real-world depth in meters. Works indoor and outdoor with ViT-Small and ViT-Large backbones.

10 runs
Public

visionaix / geocalib

GeoCalib (ECCV 2024): Single-image camera calibration. Estimates focal length, FoV, distortion, roll and pitch from one image using a deep net + Levenberg-Marquardt optimizer. Works on both outdoor and indoor scenes.

18 runs
Public