Related papers: Omni-Directional Image Generation from Single Snap…

This paper introduces MIDI, a novel paradigm for compositional 3D scene generation from a single image. Unlike existing methods that rely on reconstruction or retrieval techniques or recent approaches that employ multi-stage…

Isolating and controlling specific features in the outputs of generative models in a user-friendly way is a difficult and open-ended problem. We develop techniques that allow an oracle user to generate an image they are envisioning in their…

In this paper, we present a new perspective towards image-based shape generation. Most existing deep learning based shape reconstruction methods employ a single-view deterministic model which is sometimes insufficient to determine a single…

Given a single RGB panorama, the goal of 3D layout reconstruction is to estimate the room layout by predicting the corners, floor boundary, and ceiling boundary. A common approach has been to use standard convolutional networks to predict…

We present Omnidirectional Neural Radiance Fields (OmniNeRF), the first method to the application of parallax-enabled novel panoramic view synthesis. Recent works for novel view synthesis focus on perspective images with limited…

Omnidirectional image super-resolution (ODISR) aims to upscale low-resolution (LR) omnidirectional images (ODIs) to high-resolution (HR), catering to the growing demand for detailed visual content across a $ 180^{\circ}\times360^{\circ}$…

A recent strand of work in view synthesis uses deep learning to generate multiplane images (a camera-centric, layered 3D representation) given two or more input images at known viewpoints. We apply this representation to single-view view…

This paper provides a comprehensive survey on pioneer and state-of-the-art 3D scene geometry estimation methodologies based on single, two, or multiple images captured under the omnidirectional optics. We first revisit the basic concepts of…

Deep networks have recently enjoyed enormous success when applied to recognition and classification problems in computer vision, but their use in graphics problems has been limited. In this work, we present a novel deep architecture that…

We present a method for learning to generate unbounded flythrough videos of natural scenes starting from a single view, where this capability is learned from a collection of single photographs, without requiring camera poses or even…

Existing computer vision systems can compete with humans in understanding the visible parts of objects, but still fall far short of humans when it comes to depicting the invisible parts of partially occluded objects. Image amodal completion…

Our work aims to build a model that performs dual tasks of image captioning and image generation while being trained on only one task. The central idea is to train an invertible model that learns a one-to-one mapping between the image and…

In this paper we present an end-to-end deep learning framework to turn images that show dynamic content, such as vehicles or pedestrians, into realistic static frames. This objective encounters two main challenges: detecting all the dynamic…

Omnidirectional 360{\deg} camera proliferates rapidly for autonomous robots since it significantly enhances the perception ability by widening the field of view(FoV). However, corresponding 360{\deg} depth sensors, which are also critical…

In this paper, we propose a novel task termed Omni-Referring Image Segmentation (OmniRIS) towards highly generalized image segmentation. Compared with existing unimodally conditioned segmentation tasks, such as RIS and visual RIS, OmniRIS…

Object recognition has become a crucial part of machine learning and computer vision recently. The current approach to object recognition involves Deep Learning and uses Convolutional Neural Networks to learn the pixel patterns of the…

One-shot image generation (OSG) with generative adversarial networks that learn from the internal patches of a given image has attracted world wide attention. In recent studies, scholars have primarily focused on extracting features of…

The core of video understanding tasks, such as recognition, captioning, and tracking, is to automatically detect objects or actions in a video and analyze their temporal evolution. Despite sharing a common goal, different tasks often rely…

We propose an end-to-end learning framework for generating foreground object segmentations. Given a single novel image, our approach produces pixel-level masks for all "object-like" regions---even for object categories never seen during…

Generative Adversarial Networks (GANs) can produce images of remarkable complexity and realism but are generally structured to sample from a single latent source ignoring the explicit spatial interaction between multiple entities that could…