OpenClaw AI 技能

OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned qu

OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and attention-based decoders. Use when tra

OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a differentiable binarization approach. Use when trai

NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) wi

NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation (teacher-student) without labels and pro

Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for retrieval-based matching (e.g., retail product recog

Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attention for high-quality segmentation

Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for open-set segmentation guided by text pr

MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a ViT-

Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual representations;

PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for de

Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for language-guided detection — detects objects d

Stereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D reconstruction. Use when training, evaluating,

Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of FoundationStereo. Predicts disparity maps

DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with denoising training, multi-scale features, an

Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixel depth from single RGB images. U

Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, lighter than DINO with competitive ac

CenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF object pose estimation. Use when training

BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space, used in autonomous driving

Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video cl