Author name cluster

Xinyu Gao

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

5 papers

2 author rows

AAAI Conference 2024 Conference Paper

A General Implicit Framework for Fast NeRF Composition and Rendering

Xinyu Gao
Ziyi Yang
Yunlu Zhao
Yuxiang Sun
Xiaogang Jin
Changqing Zou

A variety of Neural Radiance Fields (NeRF) methods have recently achieved remarkable success in high render speed. However, current accelerating methods are specialized and incompatible with various implicit methods, preventing real-time composition over various types of NeRF works. Because NeRF relies on sampling along rays, it is possible to provide general guidance for acceleration. To that end, we propose a general implicit pipeline for composing NeRF objects quickly. Our method enables the casting of dynamic shadows within or between objects using analytical light sources while allowing multiple NeRF objects to be seamlessly placed and rendered together with any arbitrary rigid transformations. Mainly, our work introduces a new surface representation known as Neural Depth Fields (NeDF) that quickly determines the spatial relationship between objects by allowing direct intersection computation between rays and implicit surfaces. It leverages an intersection neural network to query NeRF for acceleration instead of depending on an explicit spatial structure.Our proposed method is the first to enable both the progressive and interactive composition of NeRF objects. Additionally, it also serves as a previewing plugin for a range of existing NeRF works.

PDF Details DOI

EAAI Journal 2024 Journal Article

An efficient method for multi-view sheep face recognition

Xiwen Zhang
Chuanzhong Xuan
Yanhua Ma
Zhaohui Tang
Xinyu Gao

Sheep face recognition is an efficient and non-contact identification technology; however, it has not been widely adopted due to the time-consuming and labor-intensive nature of traditional methods for collecting sheep face images. To address these issues, we developed a multi-view sheep face image acquisition device. A total of 50 experimental sheep were used in this study to construct a multi-view sheep face dataset. Moreover, a high-precision sheep face recognition model called T2T-ViT-SFR was developed in this study. T2T-ViT-SFR combines multiple optimization strategies to improve the performance of the model. Specifically, we introduced the Squeeze-and-Excitation (SE) attention mechanism into the backbone to enhance the model's ability to learn useful information while suppressing non-essential information. The LayerScale module was embedded in the transformer of the backbone to prevent model collapse as the network depth increased. Meanwhile, the Additive Angular Margin Loss (ArcFace) was integrated at the head to address the challenge posed by the high similarity among sheep faces. Experiments on the multi-view sheep face dataset showed that T2T-ViT-SFR achieved the best recognition performance after pre-training, with an accuracy of 95. 9% and an F1-score of 95. 5%, significantly superior to the sheep face recognition models proposed in previous studies. Compared to T2T-ViT-24, the accuracy and F1-score of T2T-ViT-SFR increased by 2. 6% and 2. 1%, respectively, demonstrating the effectiveness of the optimization strategies proposed in this study. This study provides a feasible new strategy for actual sheep identity recognition, achieving a complete recognition process from image acquisition to recognition result output.

Details DOI

NeurIPS Conference 2024 Conference Paper

RobIR: Robust Inverse Rendering for High-Illumination Scenes

Ziyi Yang
Yanzhen Chen
Xinyu Gao
Yazhen Yuan
Yu Wu
Xiaowei Zhou
Xiaogang Jin

Implicit representation has opened up new possibilities for inverse rendering. However, existing implicit neural inverse rendering methods struggle to handle strongly illuminated scenes with significant shadows and slight reflections. The existence of shadows and reflections can lead to an inaccurate understanding of the scene, making precise factorization difficult. To this end, we present RobIR, an implicit inverse rendering approach that uses ACES tone mapping and regularized visibility estimation to reconstruct accurate BRDF of the object. By accurately modeling the indirect radiance field, normal, visibility, and direct light simultaneously, we are able to accurately decouple environment lighting and the object's PBR materials without imposing strict constraints on the scene. Even in high-illumination scenes with shadows and specular reflections, our method can recover high-quality albedo and roughness with no shadow interference. RobIR outperforms existing methods in both quantitative and qualitative evaluations.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting

Ziyi Yang
Xinyu Gao
Yang-Tian Sun
Yi-Hua Huang
Xiaoyang Lyu
Wen Zhou
Shaohui Jiao
Xiaojuan Qi

The recent advancements in 3D Gaussian splatting (3D-GS) have not only facilitated real-time rendering through modern GPU rasterization pipelines but have also attained state-of-the-art rendering quality. Nevertheless, despite its exceptional rendering quality and performance on standard datasets, 3D-GS frequently encounters difficulties in accurately modeling specular and anisotropic components. This issue stems from the limited ability of spherical harmonics (SH) to represent high-frequency information. To overcome this challenge, we introduce Spec-Gaussian, an approach that utilizes an anisotropic spherical Gaussian (ASG) appearance field instead of SH for modeling the view-dependent appearance of each 3D Gaussian. Additionally, we have developed a coarse-to-fine training strategy to improve learning efficiency and eliminate floaters caused by overfitting in real-world scenes. Our experimental results demonstrate that our method surpasses existing approaches in terms of rendering quality. Thanks to ASG, we have significantly improved the ability of 3D-GS to model scenes with specular and anisotropic components without increasing the number of 3D Gaussians. This improvement extends the applicability of 3D GS to handle intricate scenarios with specular and anisotropic surfaces.

PDF Details DOI

ICRA Conference 2023 Conference Paper

Dimensional Optimization and Anti-Disturbance Analysis of an Upgraded Feed Mechanism in FAST

Xiaoyan Wang
Bin Zhang 0035
Zhaoyang Li
Xinyu Gao
Fei Zhang 0006
Yifan Ma
Rui Yao
Jianing Yin

Five-hundred-meter aperture spherical radio telescope (FAST) is a very famous large-scale scientific facility with excellent performance for astronomical observation in the world, but it currently fails to observe the center of the Milky Way Galaxy due to the limited observation angle that is affected by the heavy weight of the feed cabin. To improve this problem, an upgraded feed mechanism (UFM) with a lighter cable structure is designed and employed to replace the existing heavy rigid A-B rotator and Stewart platform in the feed cabin of FAST. The structural dimension of the UFM is analyzed and optimized under cable tension constraints to meet the requirements of the observation angle. Then, a novel disturbance increment method is proposed to analyze the anti-disturbance ability of the UFM, where a gradually increased disturbance wrench is applied to the UFM with the stiffness matrix iteratively updated. Through the dimensional optimization and further anti-disturbance analysis, the newly-designed UFM can indeed meet the higher demand for astronomical observation with the larger observation angle, which benefits from the lightweight cable structure. Besides, the UFM also has the appreciable anti-disturbance ability for long-term stable operation of FAST.

Details