Projects

CS180 Projects

Fall 2024 I took CS180/280A: Intro to Computer Vision and Computational Photography, taught by Prof. Alexei Efros. I got to work on some pretty neat projects which you can check out below.

Neural Radiance Field!

Fitting a 2D neural field and a NeRF from multi-view images, including ray generation, sampling, NeRF architecture, and volume rendering results.

Diffusion Models from Scratch!

Training UNets: unconditional, time-conditioned, and class-conditioned; results and samples.

The Power of Diffusion Models!

Diffusion sampling loops, CFG, image-to-image, visual anagrams, and hybrid images.

[Auto]stitching Photo Mosaics

Homographies, warping, rectification, feature detection/description, matching, RANSAC, Laplacian blending, and photo mosaics.

Face Morphing

Defining correspondences with landmarks, Delaunay triangulation, mid-way face, morph sequence, population mean, caricatures, and extras.

Fun with Filters and Frequencies!

Edges and DoG, unsharp masking, hybrid images, Gaussian/Laplacian stacks, multiresolution blending, and related experiments.

Colorizing the Prokudin-Gorskii Photo Collection

Aligning RGB channels using phase correlation and an image pyramid to colorize Prokudin-Gorskii glass plate photos; results across the dataset.

Misc Academic Projects

Projects from classes at Berkeley.

Investigating Demographic Attribute Representation in Vision Encoders

Probed Florence‑2’s DaViT vision encoder with linear classifiers and trained patch‑level SAEs to discover interpretable sparse dictionary features (SDFs).

Personal Projects

Smaller experiments and things I built for fun or learning.

ozanbayiz.net

This website! built with React, Next.js, Tailwind CSS, shadcn/ui, and lots and lots and lots of love.

DiT + RF

My implementation of a diffusion transformer trained on rectified flow.