Search

Your search keyword '"Li, Xinhai"' showing total 1,673 results
Start Over Author "Li, Xinhai"
1,673 results on '"Li, Xinhai"'

4. GaussianDiffusion: 3D Gaussian Splatting for Denoising Diffusion Probabilistic Models with Structured Noise

Author

Li, Xinhai, Wang, Huaibin, and Tseng, Kuo-Kun

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

Text-to-3D, known for its efficient generation methods and expansive creative potential, has garnered significant attention in the AIGC domain. However, the amalgamation of Nerf and 2D diffusion models frequently yields oversaturated images, posing severe limitations on downstream industrial applications due to the constraints of pixelwise rendering method. Gaussian splatting has recently superseded the traditional pointwise sampling technique prevalent in NeRF-based methodologies, revolutionizing various aspects of 3D reconstruction. This paper introduces a novel text to 3D content generation framework based on Gaussian splatting, enabling fine control over image saturation through individual Gaussian sphere transparencies, thereby producing more realistic images. The challenge of achieving multi-view consistency in 3D generation significantly impedes modeling complexity and accuracy. Taking inspiration from SJC, we explore employing multi-view noise distributions to perturb images generated by 3D Gaussian splatting, aiming to rectify inconsistencies in multi-view geometry. We ingeniously devise an efficient method to generate noise that produces Gaussian noise from diverse viewpoints, all originating from a shared noise source. Furthermore, vanilla 3D Gaussian-based generation tends to trap models in local minima, causing artifacts like floaters, burrs, or proliferative elements. To mitigate these issues, we propose the variational Gaussian splatting technique to enhance the quality and stability of 3D appearance. To our knowledge, our approach represents the first comprehensive utilization of Gaussian splatting across the entire spectrum of 3D content generation processes.

Published
2023

8. A transcription factor ZmGLK36 confers broad resistance to maize rough dwarf disease in cereal crops

Author

Xu, Zhennan, Zhou, Zhiqiang, Cheng, Zixiang, Zhou, Yu, Wang, Feifei, Li, Mingshun, Li, Gongjian, Li, Wenxue, Du, Qingguo, Wang, Ke, Lu, Xin, Tai, Yuxin, Chen, Runyi, Hao, Zhuanfang, Han, Jienan, Chen, Yanping, Meng, Qingchang, Kong, Xiaomin, Tie, Shuanggui, Mu, Chunhua, Song, Weibin, Wang, Zhenhua, Yong, Hongjun, Zhang, Degui, Wang, Haiyang, Weng, Jianfeng, and Li, Xinhai

Published
2023
Full Text
View/download PDF

14. Global Protected Areas as refuges for amphibians and reptiles under climate change

Author

Mi, Chunrong, Ma, Liang, Yang, Mengyuan, Li, Xinhai, Meiri, Shai, Roll, Uri, Oskyrko, Oleksandra, Pincheira-Donoso, Daniel, Harvey, Lilly P., Jablonski, Daniel, Safaei-Mahroo, Barbod, Ghaffari, Hanyeh, Smid, Jiri, Jarvie, Scott, Kimani, Ronnie Mwangi, Masroor, Rafaqat, Kazemi, Seyed Mahdi, Nneji, Lotanna Micah, Fokoua, Arnaud Marius Tchassem, Tasse Taboue, Geraud C., Bauer, Aaron, Nogueira, Cristiano, Meirte, Danny, Chapple, David G., Das, Indraneil, Grismer, Lee, Avila, Luciano Javier, Ribeiro Júnior, Marco Antônio, Tallowin, Oliver J. S., Torres-Carvajal, Omar, Wagner, Philipp, Ron, Santiago R., Wang, Yuezhao, Itescu, Yuval, Nagy, Zoltán Tamás, Wilcove, David S., Liu, Xuan, and Du, Weiguo

Published
2023
Full Text
View/download PDF

18. S3CNet: A Sparse Semantic Scene Completion Network for LiDAR Point Clouds

Author

Cheng, Ran, Agia, Christopher, Ren, Yuan, Li, Xinhai, and Bingbing, Liu

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, Computer Science - Machine Learning, Computer Science - Robotics
Abstract

With the increasing reliance of self-driving and similar robotic systems on robust 3D vision, the processing of LiDAR scans with deep convolutional neural networks has become a trend in academia and industry alike. Prior attempts on the challenging Semantic Scene Completion task - which entails the inference of dense 3D structure and associated semantic labels from "sparse" representations - have been, to a degree, successful in small indoor scenes when provided with dense point clouds or dense depth maps often fused with semantic segmentation maps from RGB images. However, the performance of these systems drop drastically when applied to large outdoor scenes characterized by dynamic and exponentially sparser conditions. Likewise, processing of the entire sparse volume becomes infeasible due to memory limitations and workarounds introduce computational inefficiency as practitioners are forced to divide the overall volume into multiple equal segments and infer on each individually, rendering real-time performance impossible. In this work, we formulate a method that subsumes the sparsity of large-scale environments and present S3CNet, a sparse convolution based neural network that predicts the semantically completed scene from a single, unified LiDAR point cloud. We show that our proposed method outperforms all counterparts on the 3D task, achieving state-of-the art results on the SemanticKITTI benchmark. Furthermore, we propose a 2D variant of S3CNet with a multi-view fusion strategy to complement our 3D network, providing robustness to occlusions and extreme sparsity in distant regions. We conduct experiments for the 2D semantic scene completion task and compare the results of our sparse 2D network against several leading LiDAR segmentation models adapted for bird's eye view segmentation on two open-source datasets., Comment: 14 pages

Published
2020

19. Changes in the Habitat Preference of Crested Ibis (Nipponia nippon) during a Period of Rapid Population Increase.

Author

Ma, Liming, Li, Xinhai, Zhai, Tianqing, Zhang, Yazu, Song, Kai, Holyoak, Marcel, and Sun, Yuehua

Subjects
animal conservation, habitat preference, interaction effects, model selection, nest site, wetland, Environmental Science and Management, Zoology, Animal Production
Abstract

The number of breeding pairs of crested ibis (Nipponia nippon) in Hanzhong, China has recovered remarkably from 2 to 511 from 1981 to 2019. Although the crested ibis has been closely monitored, the habitat preference of the bird has not been well studied despite the extensive increase in abundance. We used nest site data from the past 39 years and 30 environmental variables to develop species distribution models for each year. We applied random forest to select important environmental variables, and used logistic regressions to quantify the changes in habitat preferences in 39 years, taking into account the effects of interaction and quadratic terms. We found that six variables had strong impacts on nest site selection. The interaction term of rice paddies and waterbodies, and the quadratic term of precipitation of the wettest quarter of the year were the most important correlates of nest presence. Human impact at nest sites changed from low to high as birds increased their use of ancestral habitats with abundant rice paddies. We concluded that during the population recovery, the crested ibises retained their dependence on wetlands, yet moved from remote areas to populated rural regions where food resources had recovered due to the ban of pesticide use.

Published
2021

20. Genomic prediction of yield performance among single-cross maize hybrids using a partial diallel cross design

Author

Luo, Ping, Wang, Houwen, Ni, Zhiyong, Yang, Ruisi, Wang, Fei, Yong, Hongjun, Zhang, Lin, Zhou, Zhiqiang, Song, Wei, Li, Mingshun, Yang, Jie, Weng, Jianfeng, Meng, Zhaodong, Zhang, Degui, Han, Jienan, Chen, Yong, Zhang, Runze, Wang, Liwei, Zhao, Meng, Gao, Wenwei, Chen, Xiaoyu, Li, Wenjie, Hao, Zhuanfang, Fu, Junjie, Zhang, Xuecai, and Li, Xinhai

Published
2023
Full Text
View/download PDF

29. Deeply digging the interaction effect in multiple linear regressions using a fractional-power interaction term.

Author

Li, Xinhai, Li, Baidu, Wang, Guiming, Zhan, Xiangjiang, and Holyoak, Marcel

Subjects
Fractional-power interaction regression, InteractionFPIR, Multiple linear regression, Nonlinearity, R package, Materials Engineering
Abstract

In multiple regression Y ~ β0 + β1X1 + β2X2 + β3X1 X2 + ɛ., the interaction term is quantified as the product of X1 and X2. We developed fractional-power interaction regression (FPIR), using βX1 M X2 N as the interaction term. The rationale of FPIR is that the slopes of Y-X1 regression along the X2 gradient are modeled using the nonlinear function (Slope = β1 + β3MX1 M-1 X2 N), instead of the linear function (Slope = β1 + β3X2) that regular regressions normally implement. The ranges of M and N are from -56 to 56 with 550 candidate values, respectively. We applied FPIR using a well-studied dataset, nest sites of the crested ibis (Nipponia nippon).We further tested FPIR by other 4692 regression models. FPIRs have lower AIC values (-302 ± 5003.5) than regular regressions (-168.4 ± 4561.6), and the effect size of AIC values between FPIR and regular regression is 0.07 (95% CI: 0.04-0.10). We also compared FPIR with complex models such as polynomial regression, generalized additive model, and random forest. FPIR is flexible and interpretable, using a minimum number of degrees of freedom to maximize variance explained. We have provided a new R package, interactionFPIR, to estimate the values of M and N, and suggest using FPIR whenever the interaction term is likely to be significant. • Introduced fractional-power interaction regression (FPIR) as Y ~ β0 + β1X1 + β2X2 + β3X1 M X2 N + ɛ to replace the current regression model Y ~ β0 + β1X1 + β2X2 + β3X1 X2 + ɛ; • Clarified the rationale of FPIR, and compared it with regular regression model, polynomial regression, generalized additive model, and random forest using regression models for 4692 species; • Provided an R package, interactionFPIR, to calculate the values of M and N, and other model parameters.

Published
2020

42. Identification of the coexisting virus-derived siRNA in maize and rice infected by rice black-streaked dwarf virus

Author

Wang, Feifei, primary, Xu, Zhennan, additional, Li, Ronggai, additional, Zhou, Zhiqiang, additional, Hao, Zhuanfang, additional, Wang, Liwei, additional, Li, Mingshun, additional, Zhang, Degui, additional, Song, Wei, additional, Yong, Hongjun, additional, Han, Jienan, additional, Li, Xinhai, additional, and Weng, Jianfeng, additional

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results