← Back to Portfolio

Computer Vision Projects

Deep learning and classical image processing.

Denoising Diffusion Models

Denoising Diffusion Models

Built and trained custom UNet across 20 epochs to generate MNIST digits via DDPM. Leveraged DeepFloyd for text-conditioned generative image manipulation including inpainting, visual anagrams, and hybrid image synthesis.

View Project
Facial Keypoint Detection

Facial Keypoint Detection & HDR

Tested three CNN architectures for facial keypoints prediction: un-noised training set, pixel-noised with random transformations, and noised training set of 6000+ images.

View Project
Puffball 2D-to-3D

Puffball: 2D-to-3D Shape Construction

Transformed 2D shapes into 3D puffball models using Medial Axis Transform. Leveraged Delaunay triangulation to convert it to a mesh for surface reconstruction.

View Project
Homographies and Image Mosaicing

Image Homographies

Implemented homography transformation for novel view synthesis and image mosaic'ing, maintaining 3-pixel Euclidean distance between 150 corresponding keypoints.

View Project
Face Morphing

Face Morphing

Used Delaunay triangulation, geometric morphing, and color interpolation for seamless face transformations.

View Project
Fun with Filters and Frequencies

Fun with Filters and Frequencies

Explored filtering techniques to produce Gaussian and Laplacian stacks for image blending.

View Project
Colorizing Photos

Colorizing Photos

Transformed black and white photographs into vibrant color images with a Normalized Cross Correlation alignment algorithm.

View Project