11 papers
Articulation in Motion: Prior-free Part Mobility Analysis for Articulated Objects By Dynamic-Static Disentanglement
Hao Ai, Wenjie Chang, Jianbo Jiao +2
Articulated objects are ubiquitous in daily life. Our goal is to achieve a high-quality reconstruction, segmentation of independent moving parts, and analysis of articulation. Rece…
A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision
Hao Ai, Zidong Cao, Lin Wang
Omnidirectional image (ODI) data is captured with a field-of-view of 360x180, which is much wider than the pinhole cameras and captures richer surrounding environment details than…
CUBE360: Learning Cubic Field Representation for Monocular 360 Depth Estimation for Virtual Reality
Wenjie Chang, Hao Ai, Tianzhu Zhang +1
Panoramic images provide comprehensive scene information and are suitable for VR applications. Obtaining corresponding depth maps is essential for achieving immersive and interacti…
Elite360M: Efficient 360 Multi-task Learning via Bi-projection Fusion and Cross-task Collaboration
Hao Ai, Lin Wang
360 cameras capture the entire surrounding environment with a large FoV, exhibiting comprehensive visual information to directly infer the 3D structures, e.g., depth and surface no…
PanDA: Towards Panoramic Depth Anything with Unlabeled Panoramas and Mobius Spatial Augmentation
Zidong Cao, Jinjing Zhu, Weiming Zhang +4
Recently, Depth Anything Models (DAMs) - a type of depth foundation models - have demonstrated impressive zero-shot capabilities across diverse perspective images. Despite its succ…
Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion
Hao Ai, Lin Wang
360 depth estimation has recently received great attention for 3D reconstruction owing to its omnidirectional field of view (FoV). Recent approaches are predominantly focused on cr…
Dream360: Diverse and Immersive Outdoor Virtual Scene Creation via Transformer-Based 360 Image Outpainting
Hao Ai, Zidong Cao, Haonan Lu +6
360 images, with a field-of-view (FoV) of 180x360, provide immersive and realistic environments for emerging virtual reality (VR) applications, such as virtual tourism, where users…
OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution
Zidong Cao, Hao Ai, Yan-Pei Cao +3
Omnidirectional images (ODIs) have become increasingly popular, as their large field-of-view (FoV) can offer viewers the chance to freely choose the view directions in immersive en…
360 High-Resolution Depth Estimation via Uncertainty-aware Structural Knowledge Transfer
Zidong Cao, Hao Ai, Athanasios V. Vasilakos +1
To predict high-resolution (HR) omnidirectional depth map, existing methods typically leverage HR omnidirectional image (ODI) as the input via fully-supervised learning. However, i…
HRDFuse: Monocular 360°Depth Estimation by Collaboratively Learning Holistic-with-Regional Depth Distributions
Hao Ai, Zidong cao, Yan-pei Cao +2
Depth estimation from a monocular 360° image is a burgeoning problem owing to its holistic sensing of a scene. Recently, some methods, \eg, OmniFusion, have applied the tangent pro…
Deep Learning for Omnidirectional Vision: A Survey and New Perspectives
Hao Ai, Zidong Cao, Jinjing Zhu +3
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 conventiona…