Depth Estimation
Depth Estimation is a crucial step towards inferring scene geometry from 2D images. The goal in monocular Depth Estimation is to predict the depth value of each pixel, given only a single RGB image as input.
Image Generation
Big data has enabled deep learning algorithms achieve rapid advancements. In particular, state-of-the-art generative adversarial networks (GANs) are able to generate high-fidelity natural images of diverse categories. They are widely general methods, now starting to be applied to several other important problems, such as semisupervised learning, stabilizing sequence learning methods for speech and language, and 3D modelling. However, they still remain remarkably difficult to train, with most current papers dedicated to heuristically finding stable architectures. We are looking for a new direction designed to avoid the instability issues in GANs,
Object Placement
Object placement aims to paste the foreground on the background with suitable location, size, and shape. In previous works, object placement is used as data augmentation strategy to facilitate the downstream tasks (e.g., object detection, segmentation). There are two common methods, i.e., splicing and copy-move, to generate new composite images. Splicing is cropping the foreground object from one image and pasting it on another background image. Copy-move is removing the foreground object with inpainting techniques and pasting the foreground object at another place in the same image