Python

Overview This project is a fun exploration of the neural field and neural radiance field. In the first part, we fit a neural field to a 2D image. In the second part, we fit a neural radiance field to a 3D scene. Rendered Images Rendered Depths Part 1: Fit a Neural Field to a 2D Image In this part, we implement and train a neural field to represent a 2D image. More mathematically, we are trying to fit a neural field that: $$ F: {x, y} \rightarrow {r, g, b} $$ where $x, y$ are the coordinates of the image and $r, g, b$ are the RGB values of the image. ...

Overview This project focuses on implementing a diffusion model to generate images. The diffusion model is a generative model that generates images by iteratively applying a series of transformations to a noise image. The model is trained to generate images that are similar to the training data. The project is divided into two parts. In Part 1, we implement the forward process of the diffusion model and explore different denoising techniques using a pre-trained diffusion model. In Part 2, we train a single-step denoising UNet and extend it to include time-conditioning and class-conditioning. ...

Overview This project focuses on auto stitching photo mosaics. It is divided into two main parts: the first involves capturing source images, establishing correspondences, and manually warping and compositing them into a mosaic. The second part aims to automate the correspondence-finding process from Part 1, allowing for the efficient creation of these composite images. Automatically stitched mosaic of my deck. Automatically detected inlier matches between the two images in my living room. ...

Overview This project involves implementing face morphing and image manipulation techniques using computational photography. The primary goals are to morph an image of your face into someone else’s face, compute the average face of a given population, and create a caricature by extrapolating from the population mean. Moreover, we can change the smile of an individual by adding or subtracting a “smile vector” from their face. Finally, we can perform PCA on the face shapes of the individuals in the FEI face database and generate a laughing face by altering the PCA components. ...

Overview This project explores various techniques in image processing, focusing on 2D convolutions and frequency-based transformations. The goal is to build foundational intuitions about how filters affect images and to experiment with advanced image manipulation techniques, including sharpening, hybrid image creation, and multi-resolution blending. The image above shows the result of blending a banana and a minion using multi-resolution blending. ...