相关论文: Learning to compose 6-DoF omnidirectional videos u…

We present a novel method for generating geometrically realistic and consistent orbital videos from a single image of an object. Existing video generation works mostly rely on pixel-wise attention to enforce view consistency across frames.…

Recently, end-to-end trainable deep neural networks have significantly improved stereo depth estimation for perspective images. However, 360{\deg} images captured under equirectangular projection cannot benefit from directly adopting…

This study seeks to automate camera movement control for filming existing subjects into attractive videos, contrasting with the creation of non-existent content by directly generating the pixels. We select drone videos as our test case due…

Given a video and a set of input object masks, an omnimatte method aims to decompose the video into semantically meaningful layers containing individual objects along with their associated effects, such as shadows and reflections. Existing…

Incrementally recovering 3D dense structures from monocular videos is of paramount importance since it enables various robotics and AR applications. Feature volumes have recently been shown to enable efficient and accurate incremental dense…

Generating consistent multiple views for 3D reconstruction tasks is still a challenge to existing image-to-3D diffusion models. Generally, incorporating 3D representations into diffusion model decrease the model's speed as well as…

We propose a single-shot approach to determining 6-DoF pose of an object with available 3D computer-aided design (CAD) model from a single RGB image. Our method, dubbed MRC-Net, comprises two stages. The first performs pose classification…

Recent work on depth estimation up to now has only focused on projective images ignoring 360 content which is now increasingly and more easily produced. We show that monocular depth estimation models trained on traditional images produce…

Synthesizing high-fidelity videos from real-world multi-view input is challenging because of the complexities of real-world environments and highly dynamic motions. Previous works based on neural radiance fields have demonstrated…

Omnidirectional 3D information is essential for a wide range of applications such as Virtual Reality, Autonomous Driving, Robotics, etc. In this paper, we propose a novel, model-agnostic, two-stage pipeline for omnidirectional monocular…

Omnidirectional images, aka 360 images, can deliver immersive and interactive visual experiences. As their popularity has increased dramatically in recent years, evaluating the quality of 360 images has become a problem of interest since it…

Storage and transport of six degrees of freedom (6DoF) dynamic volumetric visual content for immersive applications requires efficient compression. ISO/IEC MPEG has recently been working on a standard that aims to efficiently code and…

Automatic saliency prediction in 360{\deg} videos is critical for viewpoint guidance applications (e.g., Facebook 360 Guide). We propose a spatial-temporal network which is (1) weakly-supervised trained and (2) tailor-made for 360{\deg}…

Portable 360$^\circ$ cameras are becoming a cheap and efficient tool to establish large visual databases. By capturing omnidirectional views of a scene, these cameras could expedite building environment models that are essential for visual…

Being data-driven is one of the most iconic properties of deep learning algorithms. The birth of ImageNet drives a remarkable trend of "learning from large-scale data" in computer vision. Pretraining on ImageNet to obtain rich universal…

Immersive maps such as Google Street View and Bing Streetside provide true-to-life views with a massive collection of panoramas. However, these panoramas are only available at sparse intervals along the path they are taken, resulting in…

Generating 3D scenes is still a challenging task due to the lack of readily available scene data. Most existing methods only produce partial scenes and provide limited navigational freedom. We introduce a practical and scalable solution…

Omnidirectional image (ODI) data is captured with a 360x180 field-of-view, which is much wider than the pinhole cameras and contains richer spatial information than the conventional planar images. Accordingly, omnidirectional vision has…

A well-known challenge in applying deep-learning methods to omnidirectional images is spherical distortion. In dense regression tasks such as depth estimation, where structural details are required, using a vanilla CNN layer on the…

Existing methods for reconstructing objects and humans from a monocular image suffer from severe mesh collisions and performance limitations for interacting occluding objects. This paper introduces a method to obtain a globally consistent…