no code implementations • 29 Sep 2024 • Shaohui Liu, Yidan Gao, Tianyi Zhang, Rémi Pautrat, Johannes L. Schönberger, Viktor Larsson, Marc Pollefeys
In this work, we introduce an incremental SfM system that, in addition to points, leverages lines and their structured geometric relations.
1 code implementation • 22 Sep 2024 • Shaohui Liu, Weiqian Cai, Hao Zhu, Brian Johnson
The growing prevalence of inverter-based resources (IBRs) for renewable energy integration and electrification greatly challenges power system dynamic analysis.
no code implementations • CVPR 2024 • Lei LI, Songyou Peng, Zehao Yu, Shaohui Liu, Rémi Pautrat, Xiaochuan Yin, Marc Pollefeys
Real-world objects and environments are predominantly composed of edge features, including straight lines and curves.
no code implementations • 2 May 2024 • Guangming Wang, Lei Pan, Songyou Peng, Shaohui Liu, Chenfeng Xu, Yanzi Miao, Wei Zhan, Masayoshi Tomizuka, Marc Pollefeys, Hesheng Wang
Meticulous 3D environment representations have been a longstanding goal in computer vision and robotics fields.
no code implementations • 23 Apr 2024 • Tong Zhang, Wenxue Cui, Shaohui Liu, Feng Jiang
Convolutional Neural Network (CNN) and Transformer have attracted much attention recently for video post-processing (VPP).
no code implementations • 29 Feb 2024 • Wenxue Cui, Xingtao Wang, Xiaopeng Fan, Shaohui Liu, Xinwei Gao, Debin Zhao
In this paper, we propose a new CNN based image CS coding framework using local structural sampling (dubbed CSCNet) that includes three functional modules: local structural sampling, measurement coding and Laplacian pyramid reconstruction.
no code implementations • 14 Jan 2024 • Honglei Xu, Yan Shu, Shaohui Liu
To overcome the problem, we propose a simple yet novel synthetic method to decouple the relationship between haze density and scene depth, by which a depth-agnostic dataset (DA-HAZE) is generated.
no code implementations • 13 Nov 2023 • Yachun Mi, Yu Li, Yan Shu, Chen Hui, Puchao Zhou, Shaohui Liu
In this paper, we propose CLiF-VQA, which considers both features related to human feelings and spatial features of videos.
1 code implementation • 2 Oct 2023 • Shaohui Liu, Hao Zhu, Vassilis Kekatos
Poorly damped oscillations pose threats to the stability and reliability of interconnected power systems.
no code implementations • 27 Sep 2023 • Petr Hruby, Shaohui Liu, Rémi Pautrat, Marc Pollefeys, Daniel Barath
We propose an approach for estimating the relative pose between calibrated image pairs by jointly exploiting points, lines, and their coincidences in a hybrid manner.
1 code implementation • ICCV 2023 • Rémi Pautrat, Shaohui Liu, Petr Hruby, Marc Pollefeys, Daniel Barath
We tackle the problem of estimating a Manhattan frame, i. e. three orthogonal vanishing points, and the unknown focal length of the camera, leveraging a prior vertical direction.
no code implementations • 19 Jul 2023 • Siyan Dong, Shaohui Liu, Hengkai Guo, Baoquan Chen, Marc Pollefeys
Visual (re)localization is critical for various applications in computer vision and robotics.
no code implementations • 2 Jun 2023 • Wenqian Cui, Xiangling Fu, Shaohui Liu, Mingjun Gu, Xien Liu, Ji Wu, Irwin King
Nevertheless, the most significant obstacle to existing disease name normalization systems is the severe shortage of training data.
1 code implementation • CVPR 2023 • Shaohui Liu, Yifan Yu, Rémi Pautrat, Marc Pollefeys, Viktor Larsson
In contrast to sparse keypoints, a handful of line segments can concisely encode the high-level scene layout, as they often delineate the main structural elements.
no code implementations • 28 Mar 2023 • Shaohui Liu, Xien Liu, Ji Wu
Under the circumstance that countries generally start to adopt DRG enrollment and payment, the problem of write-missing diagnosis is a common and serious problem.
2 code implementations • 28 Feb 2023 • Yan Shu, Shaohui Liu, Honglei Xu, Feng Jiang
Recently, developing an automatic reading system for analog measuring instruments has gained increased attention, as it enables the collection of numerous state of equipment.
no code implementations • ICCV 2023 • Zhuchen Shao, Yifeng Wang, Yang Chen, Hao Bian, Shaohui Liu, Haoqian Wang, Yongbing Zhang
Gigapixel Whole Slide Images (WSIs) aided patient diagnosis and prognosis analysis are promising directions in computational pathology.
no code implementations • 19 Dec 2022 • Young-ho Cho, Shaohui Liu, Duehee Lee, Hao Zhu
Generating wind power scenarios is very important for studying the impacts of multiple wind farms that are interconnected to the grid.
1 code implementation • 22 Sep 2022 • Shaohui Liu, Hao Zhu, Vassilis Kekatos
Wide-area dynamic studies are of paramount importance to ensure the stability and reliability of power grids.
1 code implementation • 2022 IEEE International Conference on Multimedia and Expo (ICME) 2022 • Chen Hui, Feng Jiang, Shaohui Liu, Debin Zhao
Subsequently, the content-independent SPN features of different scales are fused.
no code implementations • 3 Aug 2022 • Wenxue Cui, Shaohui Liu, Debin Zhao
By integrating certain optimization solvers with deep neural network, deep unfolding network (DUN) has attracted much attention in recent years for image compressed sensing (CS).
1 code implementation • 19 Jul 2022 • Wang Zhao, Shaohui Liu, Hengkai Guo, Wenping Wang, Yong-Jin Liu
In addition, our method is able to retain reasonable accuracy of camera poses on fully static scenes, which consistently outperforms strong state-of-the-art dense correspondence based methods with end-to-end deep learning, demonstrating the potential of dense indirect methods based on optical flow and point trajectories.
1 code implementation • 16 May 2022 • Shaohui Liu, Chengyang Wu, Hao Zhu
We develop a new topology-informed graph neural network (GNN) approach for predicting the optimal solutions of real-time ac-OPF problem.
1 code implementation • ICCV 2021 • Wang Zhao, Shaohui Liu, Yi Wei, Hengkai Guo, Yong-Jin Liu
Experimental results on ScanNet and RGB-D Scenes V2 demonstrate state-of-the-art performance of the proposed deep MVS system on multi-view depth estimation, with our proposed solver consistently improving the depth quality over both conventional and deep learning based MVS pipelines.
1 code implementation • 7 Dec 2021 • Wenxue Cui, Shaohui Liu, Feng Jiang, Debin Zhao
In this paper, a novel image CS framework using non-local neural network (NL-CSNet) is proposed, which utilizes the non-local self-similarity priors with deep network to improve the reconstruction quality.
1 code implementation • 4 Oct 2021 • Shanny Lin, Shaohui Liu, Hao Zhu
Real-time coordination of distributed energy resources (DERs) is crucial for regulating the voltage profile in distribution grids.
1 code implementation • ICCV 2021 • Yi Wei, Shaohui Liu, Yongming Rao, Wang Zhao, Jiwen Lu, Jie zhou
In this work, we present a new multi-view depth estimation method that utilizes both conventional reconstruction and learning-based priors over the recently proposed neural radiance fields (NeRF).
1 code implementation • 19 Jun 2021 • Shaohui Liu, Chengyang Wu, Hao Zhu
Solving the optimal power flow (OPF) problem in real-time electricity market improves the efficiency and reliability in the integration of low-carbon energy resources into the power grids.
1 code implementation • 25 Apr 2021 • Dongsheng Wang, Chaohao Xie, Shaohui Liu, Zhenxing Niu, WangMeng Zuo
In this paper, we present an edge-guided learnable bidirectional attention map (Edge-LBAM) for improving image inpainting of irregular holes with several distinct merits.
1 code implementation • 12 Apr 2021 • Shaohui Liu, Hao Zhu, Vassilis Kekatos
Wide-area dynamic studies are of paramount importance to ensure the stability and reliability of power grids.
no code implementations • 6 Jan 2021 • Wenxue Cui, Shaohui Liu, Feng Jiang, Yongliang Liu, Debin Zhao
The widespread application of audio communication technologies has speeded up audio data flowing across the Internet, which made it a popular carrier for covert communication.
4 code implementations • CVPR 2020 • Wang Zhao, Shaohui Liu, Yezhi Shu, Yong-Jin Liu
In this work, we tackle the essential problem of scale inconsistency for self-supervised joint depth-pose learning.
1 code implementation • CVPR 2020 • Shaohui Liu, yinda zhang, Songyou Peng, Boxin Shi, Marc Pollefeys, Zhaopeng Cui
We propose a differentiable sphere tracing algorithm to bridge the gap between inverse graphics methods and the recently proposed deep learning based implicit signed distance function.
1 code implementation • ICCV 2019 • Chaohao Xie, Shaohui Liu, Chao Li, Ming-Ming Cheng, WangMeng Zuo, Xiao Liu, Shilei Wen, Errui Ding
Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness.
Ranked #2 on Image Inpainting on Paris StreetView
6 code implementations • ICCV 2019 • Ze Yang, Shaohui Liu, Han Hu, Li-Wei Wang, Stephen Lin
They furthermore do not require the use of anchors to sample a space of bounding boxes.
Ranked #99 on Object Detection on COCO minival
no code implementations • CVPR 2019 • Yi Wei, Shaohui Liu, Wang Zhao, Jiwen Lu, Jie zhou
In this paper, we present a new perspective towards image-based shape generation.
1 code implementation • CVPR 2019 • Shaohui Liu, Xiao Zhang, Jianqiao Wangni, Jianbo Shi
We introduce the concept of normalized diversity which force the model to preserve the normalized pairwise distance between the sparse samples from a latent parametric distribution and their corresponding high-dimensional outputs.
1 code implementation • 20 Mar 2018 • Shaohui Liu, Yi Wei, Jiwen Lu, Jie zhou
Unlike most existing evaluation frameworks which transfer the representation of ImageNet inception model to map images onto the feature space, our framework uses a specialized encoder to acquire fine-grained domain-specific representation.
no code implementations • 16 Dec 2017 • Congrui Hetang, Hongwei Qin, Shaohui Liu, Junjie Yan
Video object detection is more challenging compared to image object detection.
5 code implementations • 2 Aug 2017 • Feng Jiang, Wen Tao, Shaohui Liu, Jie Ren, Xun Guo, Debin Zhao
The second CNN, named reconstruction convolutional neural network (RecCNN), is used to reconstruct the decoded image with high-quality in the decoding end.