Haiyu Zhao

Innovative Inverse-Slit Spatial-Filtering Architecture: Structural Advances for Chromatic Line Confocal Three-Dimensional Metrology

Haiyu Zhao, Shuai Wang, Jingjia Ke, Zimin An et autres

cn (code pays fourni par la source)

LaverNet: Lightweight All-in-one Video Restoration via Selective Propagation

Haiyu Zhao, Yiwen Shan, Yuanbiao Gou, Xi Peng

Recent studies have explored all-in-one video restoration, which handles multiple degradations with a unified model. However, these approaches still face two challenges when dealing with time-varying degradations. First, the degradation can dominate temporal modeling, confusing the model to focus on artifacts rather …

Playing for 3D Human Recovery

Zhongang Cai, Mingyuan Zhang, Jiawei Ren, Chen Wei et autres

Image- and video-based 3D human recovery (i.e., pose and shape estimation) have achieved substantial progress. However, due to the prohibitive cost of motion capture, existing datasets are often limited in scale and diversity. In this work, we obtain massive human sequences by …

sg, cn (code pays fourni par la source)

Exploring Point-BEV Fusion for 3D Point Cloud Object Tracking With Transformer

Zhipeng Luo, Changqing Zhou, Liang Pan, Gongjie Zhang et autres

With the prevalent use of LiDAR sensors in autonomous driving, 3D point cloud object tracking has received increasing attention. In a point cloud sequence, 3D object tracking aims to predict the location and orientation of an object in consecutive frames. Motivated by …

sg, cn (code pays fourni par la source)

Research on aerodynamic influence of contra-rotating propfan slipstream on propfan engine nacelle inlet

Haiyu Zhao, Zhou Li, Wenjian Deng, Zhanxue Wang

Abstract In order to investigate the aerodynamic influence of contra-rotating propfan (CRP) slipstream on propfan engine nacelle, numerical simulation research on the CRP/Nacelle integrated configuration was carried out by using sliding mesh unsteady method. The aerodynamic performance of integrated configuration under different …

cn (code pays fourni par la source)

Test-Time Degradation Adaptation for Open-Set Image Restoration

Yuanbiao Gou, Haiyu Zhao, Boyun Li, Xinyan Xiao et autres

In contrast to close-set scenarios that restore images from a predefined set of degradations, open-set image restoration aims to handle the unknown degradations that were unforeseen during the pretraining phase, which is less-touched as far as we know. This work study this …

ABLE-NeRF: Attention-Based Rendering with Learnable Embeddings for Neural Radiance Field

Zhe Jun Tang, Tat‐Jen Cham, Haiyu Zhao

Neural Radiance Field (NeRF) is a popular method in representing 3D scenes by optimising a continuous volumetric scene function. Its large success which lies in applying volumetric rendering (VR) is also its Achilles' heel in producing view-dependent effects. As a consequence, glossy …

sg, cn, ch (code pays fourni par la source)

Multi-Stage Sequential Network Energy Control for offshore AC asymmetric fault ride-through of MMC-HVDC system integrated offshore wind farms

Haiyu Zhao, Hongyu Zhou, Wei Yao, Qihang Zong et autres

cn (code pays fourni par la source)

Variational Relational Point Completion Network for Robust 3D Classification

Liang Pan, Xinyi Chen, Zhongang Cai, Junzhe Zhang et autres

Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise, which hampers 3D geometric modeling and perception. Existing point cloud completion methods tend to generate global shape skeletons and hence lack fine local details. Furthermore, they mostly learn a deterministic …

sg, cn (code pays fourni par la source)

Variational Relational Point Completion Network for Robust 3D Classification

Liang Pan, Xinyi Chen, Zhongang Cai, Junzhe Zhang et autres

Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise, which hampers 3D geometric modeling and perception. Existing point cloud completion methods tend to generate global shape skeletons and hence lack fine local details. Furthermore, they mostly learn a deterministic …

ABLE-NeRF: Attention-Based Rendering with Learnable Embeddings for Neural Radiance Field

Zhe Jun Tang, Tat‐Jen Cham, Haiyu Zhao

Neural Radiance Field (NeRF) is a popular method in representing 3D scenes by optimising a continuous volumetric scene function. Its large success which lies in applying volumetric rendering (VR) is also its Achilles' heel in producing view-dependent effects. As a consequence, glossy …

IntegratedPIFu: Integrated Pixel Aligned Implicit Function for Single-view Human Reconstruction

Kennard Yanting Chan, Guosheng Lin, Haiyu Zhao, Weisi Lin

We propose IntegratedPIFu, a new pixel aligned implicit model that builds on the foundation set by PIFuHD. IntegratedPIFu shows how depth and human parsing information can be predicted and capitalised upon in a pixel-aligned implicit model. In addition, IntegratedPIFu introduces depth oriented …