Computer vision
Graduate · CS / Programming
Syllabus focus
Standard syllabus · STEM / applied
Pricing
Graduate-level rates are set on consultation. See the pricing page for K–12 and undergraduate rates.
Topics typically covered
Standard syllabus
Imaging foundations
- Pinhole camera model and calibration (intro)
- Filtering, edge detection, and convolution
- Color spaces and histogram methods
- Feature descriptors: SIFT/HOG (survey)
- Stereo and depth from motion (intro)
Recognition pipelines
- Image classification with CNNs
- Object detection: R-CNN family survey
- Segmentation: semantic and instance (intro)
- Transfer learning and fine-tuning
- Data augmentation and dataset bias
STEM / applied
Projects and 3D
- Training pipelines with PyTorch/TensorFlow
- Video understanding and tracking (intro)
- Pose estimation and keypoints (intro)
- NeRF and 3D vision trends (survey)
- Real-time inference on edge devices
Responsible vision
- Fairness in face recognition systems
- Adversarial examples and robustness
- Privacy-preserving vision (intro)
- Medical imaging workflow considerations
- Capstone: Kaggle-style competition project
Notes
Requires linear algebra, probability, and ML background. Classical geometry content varies.