no code implementations • 17 Jan 2023 • Xiang-Li Li, Meng-Hao Guo, Tai-Jiang Mu, Ralph R. Martin, Shi-Min Hu
To achieve the above properties, we propose a simple yet effective long range pooling (LRP) module using dilation max pooling, which provides a network with a large adaptive receptive field.
3 code implementations • 18 Sep 2022 • Meng-Hao Guo, Cheng-Ze Lu, Qibin Hou, ZhengNing Liu, Ming-Ming Cheng, Shi-Min Hu
Notably, SegNeXt outperforms EfficientNet-L2 w/ NAS-FPN and achieves 90. 6% mIoU on the Pascal VOC 2012 test leaderboard using only 1/10 parameters of it.
no code implementations • 4 May 2022 • Xian Wu, Chen Wang, Hongbo Fu, Ariel Shamir, Song-Hai Zhang, Shi-Min Hu
Researchers have explored various ways to generate realistic images from freehand sketches, e. g., for objects and human faces.
17 code implementations • 20 Feb 2022 • Meng-Hao Guo, Cheng-Ze Lu, Zheng-Ning Liu, Ming-Ming Cheng, Shi-Min Hu
In this paper, we propose a novel linear attention named large kernel attention (LKA) to enable self-adaptive and long-range correlations in self-attention while avoiding its shortcomings.
Ranked #1 on Panoptic Segmentation on COCO panoptic
1 code implementation • 3 Dec 2021 • Chen Wang, Xian Wu, Yuan-Chen Guo, Song-Hai Zhang, Yu-Wing Tai, Shi-Min Hu
We present NeRF-SR, a solution for high-resolution (HR) novel view synthesis with mostly low-resolution (LR) inputs.
1 code implementation • 25 Nov 2021 • Jiahui Huang, Tolga Birdal, Zan Gojcic, Leonidas J. Guibas, Shi-Min Hu
We present SyNoRiM, a novel way to jointly register multiple non-rigid shapes by synchronizing the maps relating learned functions defined on the point clouds.
no code implementations • 25 Nov 2021 • Haoxiang Chen, Jiahui Huang, Tai-Jiang Mu, Shi-Min Hu
We present CIRCLE, a framework for large-scale scene completion and geometric refinement based on local implicit signed distance functions.
2 code implementations • 15 Nov 2021 • Meng-Hao Guo, Tian-Xing Xu, Jiang-Jiang Liu, Zheng-Ning Liu, Peng-Tao Jiang, Tai-Jiang Mu, Song-Hai Zhang, Ralph R. Martin, Ming-Ming Cheng, Shi-Min Hu
Humans can naturally and effectively find salient regions in complex scenes.
no code implementations • 5 Nov 2021 • Guo-Ye Yang, Xiang-Li Li, Ralph R. Martin, Shi-Min Hu
Sampling equivariant networks can adjust sampling from input feature maps according to the transformation of the object, allowing a kernel to extract features of an object under different transformations.
1 code implementation • 4 Jun 2021 • Shi-Min Hu, Zheng-Ning Liu, Meng-Hao Guo, Jun-Xiong Cai, Jiahui Huang, Tai-Jiang Mu, Ralph R. Martin
Meshes with arbitrary connectivity can be remeshed to have Loop subdivision sequence connectivity via self-parameterization, making SubdivNet a general approach.
no code implementations • 31 May 2021 • Meng-Hao Guo, Zheng-Ning Liu, Tai-Jiang Mu, Dun Liang, Ralph R. Martin, Shi-Min Hu
In the first week of May, 2021, researchers from four different institutions: Google, Tsinghua University, Oxford University and Facebook, shared their latest work [16, 7, 12, 17] on arXiv. org almost at the same time, each proposing new learning architectures, consisting mainly of linear layers, claiming them to be comparable, or even superior to convolutional-based models.
1 code implementation • 19 May 2021 • Guo-Wei Yang, Wen-Yang Zhou, Hao-Yang Peng, Dun Liang, Tai-Jiang Mu, Shi-Min Hu
Only query coordinates with high uncertainties are forwarded to the next level to a bigger neural network with a more powerful representational capability.
6 code implementations • 5 May 2021 • Meng-Hao Guo, Zheng-Ning Liu, Tai-Jiang Mu, Shi-Min Hu
Attention mechanisms, especially self-attention, have played an increasingly important role in deep feature representation for visual tasks.
Ranked #16 on Semantic Segmentation on PASCAL VOC 2012 test
1 code implementation • CVPR 2021 • Jiahui Huang, He Wang, Tolga Birdal, Minhyuk Sung, Federica Arrigoni, Shi-Min Hu, Leonidas Guibas
We present MultiBodySync, a novel, end-to-end trainable multi-body motion segmentation and rigid registration framework for multiple input 3D point clouds.
9 code implementations • 17 Dec 2020 • Meng-Hao Guo, Jun-Xiong Cai, Zheng-Ning Liu, Tai-Jiang Mu, Ralph R. Martin, Shi-Min Hu
It is inherently permutation invariant for processing a sequence of points, making it well-suited for point cloud learning.
Ranked #2 on 3D Point Cloud Classification on IntrA
1 code implementation • CVPR 2021 • Jiahui Huang, Shi-Sheng Huang, Haoxuan Song, Shi-Min Hu
Previous online 3D dense reconstruction methods struggle to achieve the balance between memory storage and surface quality, largely due to the usage of stagnant underlying geometry representation, such as TSDF (truncated signed distance functions) or surfels, without any knowledge of the scene priors.
no code implementations • 14 Jun 2020 • Congyue Deng, Tai-Jiang Mu, Shi-Min Hu
Experimental results show that Alt-ConvLSTM efficiently models the material kinetic features and greatly outperforms vanilla ConvLSTM with only the single state update.
no code implementations • CVPR 2020 • Jiahui Huang, Sheng Yang, Tai-Jiang Mu, Shi-Min Hu
We present ClusterVO, a stereo Visual Odometry which simultaneously clusters and estimates the motion of both ego and surrounding rigid clusters/objects.
no code implementations • 22 Feb 2020 • Yinyu Nie, Shihui Guo, Jian Chang, Xiaoguang Han, Jiahui Huang, Shi-Min Hu, Jian Jun Zhang
Particularly, we design a shallow-to-deep architecture on the basis of convolutional networks for semantic scene understanding and modeling.
2 code implementations • 30 Nov 2019 • Minghua Liu, Lu Sheng, Sheng Yang, Jing Shao, Shi-Min Hu
3D point cloud completion, the task of inferring the complete geometric shape from a partial point cloud, has been attracting attention in the community.
Ranked #5 on Point Cloud Completion on ShapeNet
1 code implementation • 4 Jun 2019 • Miao Wang, Guo-Ye Yang, Rui-Long Li, Run-Ze Liang, Song-Hai Zhang, Peter. M. Hall, Shi-Min Hu
Example-guided image synthesis aims to synthesize an image from a semantic label map and an exemplary image indicating style.
no code implementations • 6 May 2019 • Sen-Zhe Xu, Hao-Zhi Huang, Shi-Min Hu, Wei Liu
On the basis of the FaceShapeGene, a novel part-wise face image editing system is developed, which contains a shape-remix network and a conditional label-to-face transformer.
no code implementations • 24 Nov 2018 • Song-Hai Zhang, Zhengping Zhou, Bin Liu, Xin Dong, Dun Liang, Peter Hall, Shi-Min Hu
In this work, we propose a novel topic consisting of two dual tasks: 1) given a scene, recommend objects to insert, 2) given an object category, retrieve suitable background scenes.
2 code implementations • 1 Oct 2018 • Yu-Ping Wang, Wende Tan, Xu-Qiang Hu, Dinesh Manocha, Shi-Min Hu
We show that by using TZC, the braking distance can be shortened by 16% than ROS.
1 code implementation • 5 Sep 2018 • Hao-Zhi Huang, Senzhe Xu, Junxiong Cai, Wei Liu, Shi-Min Hu
Since existing video datasets which have ground-truth foreground masks and optical flows are not sufficiently large, we propose a simple yet efficient method to build up a synthetic dataset supporting supervised training of the proposed adversarial network.
no code implementations • ECCV 2018 • Yan-Pei Cao, Zheng-Ning Liu, Zheng-Fei Kuang, Leif Kobbelt, Shi-Min Hu
We present a data-driven approach to reconstructing high-resolution and detailed volumetric representations of 3D shapes.
no code implementations • ECCV 2018 • Ruochen Fan, Qibin Hou, Ming-Ming Cheng, Gang Yu, Ralph R. Martin, Shi-Min Hu
We also combine our method with Mask R-CNN for instance segmentation, and demonstrated for the first time the ability of weakly supervised instance segmentation using only keyword annotations.
Ranked #3 on Image-level Supervised Instance Segmentation on COCO test-dev (using extra training data)
graph partitioning Image-level Supervised Instance Segmentation +4
no code implementations • 23 Aug 2018 • Xian Wu, Rui-Long Li, Fang-Lue Zhang, Jian-Cheng Liu, Jue Wang, Ariel Shamir, Shi-Min Hu
We evaluate our method on public portrait image datasets, and show that it outperforms other state-of-art general image completion methods.
no code implementations • 16 Jul 2018 • Dun Liang, Yuanchen Guo, Shaokui Zhang, Song-Hai Zhang, Peter Hall, Min Zhang, Shi-Min Hu
Combining LineNet and TTLane, we proposed a pipeline to model HD maps with crowdsourced data for the first time.
6 code implementations • CVPR 2019 • Song-Hai Zhang, Rui-Long Li, Xin Dong, Paul L. Rosin, Zixi Cai, Han Xi, Dingcheng Yang, Hao-Zhi Huang, Shi-Min Hu
We demonstrate that our pose-based framework can achieve better accuracy than the state-of-art detection-based approach on the human instance segmentation problem, and can moreover better handle occlusion.
Ranked #1 on Human Instance Segmentation on OCHuman
5 code implementations • 28 Feb 2018 • Tai-Ling Yuan, Zhe Zhu, Kun Xu, Cheng-Jun Li, Shi-Min Hu
[python3. 6] 运用tf实现自然场景文字检测, keras/pytorch实现ctpn+crnn+ctc实现不定长场景文字OCR识别
3 code implementations • 22 Feb 2018 • Miao Wang, Guo-Ye Yang, Jin-Kun Lin, Ariel Shamir, Song-Hai Zhang, Shao-Ping Lu, Shi-Min Hu
In this paper, we solve the video stabilization problem using a convolutional neural network (ConvNet).
1 code implementation • CVPR 2019 • Ruochen Fan, Ming-Ming Cheng, Qibin Hou, Tai-Jiang Mu, Jingdong Wang, Shi-Min Hu
Taking into account the category-independent property of each target, we design a single stage salient instance segmentation framework, with a novel segmentation branch.
no code implementations • 1 Jun 2016 • Zhe Zhu, Jiaming Lu, Minxuan Wang, Song-Hai Zhang, Ralph Martin, Hantao Liu, Shi-Min Hu
In this paper, we investigate 6 popular blending algorithms---feather blending, multi-band blending, modified Poisson blending, mean value coordinate blending, multi-spline blending and convolution pyramid blending.
no code implementations • 21 Mar 2016 • Liqian Ma, Jue Wang, Eli Shechtman, Kalyan Sunkavalli, Shi-Min Hu
In this work we propose a fully automatic shadow region harmonization approach that improves the appearance compatibility of the de-shadowed region as typically produced by previous methods.
no code implementations • ACM Transactions on Graphics 2009 • Tao Chen, Ming-Ming Cheng, Ping Tan, Ariel Shamir, Shi-Min Hu
The composed picture is generated by seamlessly stitching several photographs in agreement with the sketch and text labels; these are found by searching the Internet.