Qixing Huang

3D Vision

The field of 3D Vision focuses on recovering 3D structures from RGB/RGB-D images. While traditionally this field studies 3D reconstruction from images, recent works have focused on treating 3D geometry as a modality for 3D understanding. My past research studied a variety of topics in 3D Vision, such as 6D object pose estimation[CVPR19b][CVPR20b], human pose estimation[ICCV17][CVPR19a], 3D object detection[Arxiv20], keypoint prediction[ECCV18a][ECCV18b], monocular shape reconstruction[SIG14][SIG15], relative pose estimation[CVPR19c][CVPR20a], generative shape modeling[CVPR17], shape classification[3DV17], and shape matching[CVPR16].

IAE_2022

[ARXIV22a] Siming Yan, Zhenpei Yang, Haoxiang Li, Li Guan, Hao Kang, Gang Hua,and Qixing Huang. Implicit Autoencoder for Point Cloud Self-supervised Representation Learning. https://arxiv.org/abs/2201.00785x

InfoGCN_2022

[CVPR22a] Hyung-gun Chi, Myoung Hoon Ha, Seunggeun Ch, Sang Wan Lee, Qixing Huang, and Karthik Ramani. InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition. Computer Vision and Pattern Recognition (or CVPR) 2022

MVS2D_2021

[CVPR22b] Zhenpei Yang, Zhile Ren, Qi Shan, and Qixing Huang. MVS2D: Efficient Multi-view Stereo via Attention-Driven 2D Convolutions. Computer Vision and Pattern Recognition (or CVPR) 2022

FvOR_2022

[CVPR22c] Zhenpei Yang, Zhile Ren, Miguel Angel Bautista, Zaiwei Zhang, Qi Shan, and Qixing Huang. FvOR: Robust Joint Shape and Pose Optimization for Few-view Object Reconstruction. Computer Vision and Pattern Recognition (or CVPR) 2022

HM3D-ABO_2022

[ARXIV22b] Zhenpei Yang, Zaiwei Zhang, and Qixing Huang. HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction. https://arxiv.org/abs/2206.12356

HPNet_2021

[ICCV21a] Siming Yan, Zhenpei Yang, Chongyang Ma, Haibin Huang, Etienne Vouga, and Qixing Huang. HPNet: Deep Primitive Segmentation Using Hybrid Representations. International Conference on Computer Vision (or ICCV) 2021.

arxiv_human

[PAMI21a] Junting Dong, Wen Jiang, Qixing Huang, Hujun Bao, and Xiaowei Zhou. Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views. IEEE Transactions on Pattern Recognition and Machine Intelligence (or PAMI) 2021, to appear.

SIGGRAPH_2021

[SIG21] Scalable Image-based Indoor Scene Rendering with Reflections. Conditionally Accepted to ACM SIGGRAPH 2021.

[CVPR21a] Yifan Sun, Qixing Huang, Dun-Yu Hsiao, Li Guan, and Gang Hua. Learning View Selection for 3D Scenes. Computer Vision and Pattern Recognition (CVPR), 2021.

[CVPR21b] Zhenpei Yang, Li Erran Li, and Qixing Huang. StruMonoNet: Structure-Aware Monocular 3D Prediction. Computer Vision and Pattern Recognition (CVPR), 2021.

NeurIPS_2020

Xiangru Huang, Haitao Yang, Etienne Vouga, and Qixing Huang. Dense Human Correspondence via Learning Transformation Synchronization on Graphs. Advances in Neural Information Processing Systems(NeurIPS), 2020.

Arxiv_H3DNet

[ECCV20a] Zaiwei Zhang, Bo Sun, Haitao Yang, and Qixing Huang. H3DNet: 3D Object Detection Using Hybrid Geometric Primitives. arXiv:2006.05682.

MCB_Benchmark

[ECCV20b] Sangpil Kim, Hyung-gun Chi, Xiao Hu, Qixing Huang, and Karthik Ramani. A Large-scale Annotated Mechanical Components Benchmark for Classification and Retrieval Tasks with Deep Neural Networks. European Conference on COMPUTER VISION ( ECCV ) 2020. Benchmark website

hybrid_pose

[CVPR20b] Chen Song, Jiaru Song, and Qixing Huang. HybridPose: 6D Object Pose Estimation under Hybrid Representations Computer Vision and Pattern Recognition (or CVPR) 2020.

hybrid_rel_pose

[CVPR20a] Zhenpei Yang, Siming Yan, and Qixing Huang. Extreme Relative Pose Network under Hybrid Representations Computer Vision and Pattern Recognition (or CVPR) 2020. Oral Presentation .

arxiv_pose

[CVPR19c] Zhenpei Yang, Jeffrey Z.Pan, Linjie Luo, Xiaowei Zhou, Kristen Grauman, and Qixing Huang. Extreme Relative Pose Estimation for RGB-D Scans via Scene Completion. Computer Vision and Pattern Recognition (or CVPR) 2019. Oral Presentation .

arxiv_object

[CVPR19b] Sida Peng, Yuan Liu, Qixing Huang, Hujun Bao, and Xiaowei Zhou. PVNet: Pixel-wise Voting Network for 6DoF Pose Estimation. Computer Vision and Pattern Recognition (or CVPR) 2019. Oral Presentation .

arxiv_human

[CVPR19a] Junting Dong, Wen Jiang, Qixing Huang, Hujun Bao, and Xiaowei Zhou. Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views. Computer Vision and Pattern Recognition (or CVPR) 2019.

KEYPTS_DA_17

[ECCV18b] Xingyi Zhou, Arjun Karpur, Chuang Gan, Linjie Luo, and Qixing Huang. Unsupervised Domain Adaptation for 3D Keypoint Prediction from a Single Depth Scan. European Conference on Computer Vision 2018 (or ECCV 2018).

STARMAP_18

[ECCV18a] Xingyi Zhou, Arjun Karpur, Linjie Luo, and Qixing Huang. StarMap for Category-Agnostic Keypoint and Viewpoint Estimation. European Conference on Computer Vision 2018 (or ECCV 2018).

sphere

[3DV17] Zhangjie Cao, Qixing Huang and Karthik Ramani. 3D Object Classification via Spherical Projections. International Conference on 3D Vision 2017. Spotlight Presentation.

[ICCV17] Xingyi Zhou, Qixing Huang, Xiao Sun, Xiangyang Xue, and Yichen Wei. Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach. . International Conference on Computer Vision' 2017.

[CVPR17] Ayan Sinha, Asim Unmesh, Qixing Huang, and Karthik Ramani. SurfNet: Generating 3D shape surfaces using deep residual networks. Computer Vision and Pattern Recognition' 2017.

[CVPR16] Linyu Wei, Qixing Huang, Duygu Ceylan, Etienne Vouga, and Hao Li. Dense Human Body Correspondences Using Convolutional Networks. IEEE Conference on Computer Vision and Pattern Recognition 2016 (Oral Presentation).

sig15_ibm

[SIG15] Qixing Huang, Hai Wang, and Vladlen Koltun. Single-View Reconstruction via Joint Analysis of Image and Shape Collections. ACM Transaction on Graphics 34(4) (Proc. Siggraph 2015).

Code

sig14_depth

[SIG14] Su Hao, Qixing Huang, Niloy Mitra, Yangyan Li, and Leonidas Guibas. Estimating Image Depth Using Shape Collections. ACM Transaction on Graphics 33(4) (Proc. Siggraph 2014).