183 citations · 318 across the 13 of their papers we have counts for
14 papers · 1 filter
Spatial Transform Decoupling for Oriented Object Detection
Hongtian Yu, Yunjie Tian, Qixiang Ye +1
Vision Transformers (ViTs) have achieved remarkable success in computer vision tasks. However, their potential in rotation-sensitive scenarios has not been fully explored, and this…
Learning Object-Centric Neural Scattering Functions for Free-Viewpoint Relighting and Scene Composition
Hong-Xing Yu, Michelle Guo, Alireza Fathi +5
Photorealistic object appearance modeling from 2D images is a constant topic in vision and graphics. While neural implicit methods (such as Neural Radiance Fields) have shown high-…
Accidental Light Probes
Hong-Xing Yu, Samir Agarwala, Charles Herrmann +4
Recovering lighting in a scene from a single image is a fundamental problem in computer vision. While a mirror ball light probe can capture omnidirectional lighting, light probes a…
Unsupervised Discovery and Composition of Object Light Fields
Cameron Smith, Hong-Xing Yu, Sergey Zakharov +4
Neural scene representations, both continuous and discrete, have recently emerged as a powerful new paradigm for 3D scene understanding. Recent efforts have tackled unsupervised di…
Rotationally Equivariant 3D Object Detection
Hong-Xing Yu, Jiajun Wu, Li Yi
Rotation equivariance has recently become a strongly desired property in the 3D deep learning community. Yet most existing methods focus on equivariance regarding a global input ro…
Letter-level Online Writer Identification
Zelin Chen, Hong-Xing Yu, Ancong Wu +1
Writer identification (writer-id), an important field in biometrics, aims to identify a writer by their handwriting. Identification in existing writer-id studies requires a complet…