Learning Structured Output Representations from Attributes using Deep Conditional Generative Models

Structured output representation is a generative task explored in computer vision that often times requires the mapping of low dimensional features to high dimensional structured outputs. Losses in complex spatial information in deterministic approaches such as Convolutional Neural Networks (CNN) lead to uncertainties and ambiguous structures within a single output representation. A probabilistic approach through deep Conditional Generative Models (CGM) is presented by Sohn et al. in which a particular model known as the Conditional Variational Auto-encoder (CVAE) is introduced and explored. While the original paper focuses on the task of image segmentation, this paper adopts the CVAE framework for the task of controlled output representation through attributes. This approach allows us to learn a disentangled multimodal prior distribution, resulting in more controlled and robust approach to sample generation. In this work we recreate the CVAE architecture and train it on images conditioned on various attributes obtained from two image datasets; the Large-scale CelebFaces Attributes (CelebA) dataset and the Caltech-UCSD Birds (CUB-200-2011) dataset. We attempt to generate new faces with distinct attributes such as hair color and glasses, as well as different bird species samples with various attributes. We further introduce strategies for improving generalized sample generation by applying a weighted term to the variational lower bound.

Neural Radiance Fields (NeRFs): A Review and Some Recent Developments

Neural Radiance Field (NeRF) is a framework that represents a 3D scene in the weights of a fully connected neural network, known as the Multi-Layer Perception(MLP). The method was introduced for the task of novel view synthesis and is able to achieve state-of-the-art photorealistic image renderings from a given continuous viewpoint. NeRFs have become a popular field of research as recent developments have been made that expand the performance and capabilities of the base framework. Recent developments include methods that require less images to train the model for view synthesis as well as methods that are able to generate views from unconstrained and dynamic scene representations.