学术成果
Selected Publications (See Google Scholar Citations page)
2020
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation Inproceedings
In: Larochelle, Hugo; Ranzato, Marc'Aurelio; Hadsell, Raia; Balcan, Maria-Florina; Lin, Hsuan-Tien (Ed.): Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual, 2020.
High frame rate video reconstruction based on an event camera Journal Article
In: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020.
2019
Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene Journal Article
In: IEEE Trans. Pattern Anal. Mach. Intell., vol. 43, no. 5, pp. 1705–1717, 2019.
Deeply Supervised Depth Map Super-Resolution as Novel View Synthesis Journal Article
In: IEEE Trans. Circuits Syst. Video Technol., vol. 29, no. 8, pp. 2323–2336, 2019.
MVS2: Deep Unsupervised Multi-View Stereo with Multi-View Symmetry Inproceedings
In: 2019 International Conference on 3D Vision, 3DV 2019, Québec City, QC, Canada, September 16-19, 2019, pp. 1–8, IEEE, 2019.
IoU Loss for 2D/3D Object Detection Inproceedings
In: 2019 International Conference on 3D Vision, 3DV 2019, Québec City, QC, Canada, September 16-19, 2019, pp. 85–94, IEEE, 2019.
SDBF-Net: Semantic and Disparity Bidirectional Fusion Network for 3D Semantic Detection on Incidental Satellite Images Inproceedings
In: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019, Lanzhou, China, November 18-21, 2019, pp. 438–444, IEEE, 2019.
MSDC-Net: Multi-Scale Dense and Contextual Networks for Stereo Matching Inproceedings
In: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2019, Lanzhou, China, November 18-21, 2019, pp. 578–583, IEEE, 2019.
ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving Inproceedings
In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 5452–5462, Computer Vision Foundation / IEEE, 2019.
Deep Stacked Hierarchical Multi-Patch Network for Image Deblurring Inproceedings
In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 5978–5986, Computer Vision Foundation / IEEE, 2019.
Phase-Only Image Based Kernel Estimation for Single Image Blind Deblurring Inproceedings
In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 6034–6043, Computer Vision Foundation / IEEE, 2019.
Noise-Aware Unsupervised Deep Lidar-Stereo Fusion Inproceedings
In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 6339–6348, Computer Vision Foundation / IEEE, 2019.
Bringing a Blurry Frame Alive at High Frame-Rate With an Event Camera Inproceedings
In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 6820–6829, Computer Vision Foundation / IEEE, 2019.
Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes Inproceedings
In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2019, Long Beach, CA, USA, June 16-20, 2019, pp. 12095–12104, Computer Vision Foundation / IEEE, 2019.
Stochastic Attraction-Repulsion Embedding for Large Scale Image Localization Inproceedings
In: 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019, Seoul, Korea (South), October 27 - November 2, 2019, pp. 2570–2579, IEEE, 2019.
Single Image Deblurring and Camera Motion Estimation With Depth Map Inproceedings
In: IEEE Winter Conference on Applications of Computer Vision, WACV 2019, Waikoloa Village, HI, USA, January 7-11, 2019, pp. 2116–2125, IEEE, 2019.
2018
3D skeleton based action recognition by video-domain translation-scale invariant mapping and multi-scale dilated CNN Journal Article
In: Multim. Tools Appl., vol. 77, no. 17, pp. 22901–22921, 2018.
Monocular depth estimation with hierarchical fusion of dilated CNNs and soft-weighted-sum inference Journal Article
In: Pattern Recognit., vol. 83, pp. 328–339, 2018.
Robust and Efficient Relative Pose With a Multi-Camera System for Autonomous Driving in Highly Dynamic Environments Journal Article
In: IEEE Trans. Intell. Transp. Syst., vol. 19, no. 8, pp. 2432–2444, 2018.
Scalable Dense Non-Rigid Structure-From-Motion: A Grassmannian Perspective Inproceedings
In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 254–263, IEEE Computer Society, 2018.
Deep Unsupervised Saliency Detection: A Multiple Noisy Labeling Perspective Inproceedings
In: 2018 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2018, Salt Lake City, UT, USA, June 18-22, 2018, pp. 9029–9038, IEEE Computer Society, 2018.
Open-World Stereo Video Matching with Deep RNN Inproceedings
In: Ferrari, Vittorio; Hebert, Martial; Sminchisescu, Cristian; Weiss, Yair (Ed.): Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part II, pp. 104–119, Springer, 2018.
Stereo Computation for a Single Mixture Image Inproceedings
In: Ferrari, Vittorio; Hebert, Martial; Sminchisescu, Cristian; Weiss, Yair (Ed.): Computer Vision - ECCV 2018 - 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part IX, pp. 441–456, Springer, 2018.
Occluded Joints Recovery in 3D Human Pose Estimation based on Distance Matrix Inproceedings
In: 24th International Conference on Pattern Recognition, ICPR 2018, Beijing, China, August 20-24, 2018, pp. 1325–1330, IEEE Computer Society, 2018.
3D Geometry-Aware Semantic Labeling of Outdoor Street Scenes Inproceedings
In: 24th International Conference on Pattern Recognition, ICPR 2018, Beijing, China, August 20-24, 2018, pp. 2343–2349, IEEE Computer Society, 2018.
Depth Map Completion by Jointly Exploiting Blurry Color Images and Sparse Depth Maps Inproceedings
In: 2018 IEEE Winter Conference on Applications of Computer Vision, WACV 2018, Lake Tahoe, NV, USA, March 12-15, 2018, pp. 1377–1386, IEEE Computer Society, 2018.
2017
Moving object detection and segmentation in urban environments from a moving platform Journal Article
In: Image Vis. Comput., vol. 68, pp. 76–87, 2017.
Spatio-temporal union of subspaces for multi-body non-rigid structure-from-motion Journal Article
In: Pattern Recognit., vol. 71, pp. 428–443, 2017.
Multi-scale salient object detection with pyramid spatial pooling Inproceedings
In: 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, APSIPA ASC 2017, Kuala Lumpur, Malaysia, December 12-15, 2017, pp. 1286–1291, IEEE, 2017.
Simultaneous Stereo Video Deblurring and Scene Flow Estimation Inproceedings
In: 2017 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, Honolulu, HI, USA, July 21-26, 2017, pp. 6987–6996, IEEE Computer Society, 2017.
Attention to the Scale: Deep Multi-Scale Salient Object Detection Inproceedings
In: 2017 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2017, Sydney, Australia, November 29 - December 1, 2017, pp. 1–7, IEEE, 2017.
In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017, pp. 929–937, IEEE Computer Society, 2017.
Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map Inproceedings
In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017, pp. 2391–2400, IEEE Computer Society, 2017.
Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames Inproceedings
In: IEEE International Conference on Computer Vision, ICCV 2017, Venice, Italy, October 22-29, 2017, pp. 4659–4667, IEEE Computer Society, 2017.
Integrated deep and shallow networks for salient object detection Inproceedings
In: 2017 IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, September 17-20, 2017, pp. 1537–1541, IEEE, 2017.
Dense non-rigid structure-from-motion made easy - A spatial-temporal smoothness based solution Inproceedings
In: 2017 IEEE International Conference on Image Processing, ICIP 2017, Beijing, China, September 17-20, 2017, pp. 4532–4536, IEEE, 2017.
Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep CNN Inproceedings
In: 2017 IEEE International Conference on Multimedia & Expo Workshops, ICME Workshops, Hong Kong, China, July 10-14, 2017, pp. 601–604, IEEE Computer Society, 2017.
Skeleton boxes: Solving skeleton based action detection with a single deep convolutional neural network Inproceedings
In: 2017 IEEE International Conference on Multimedia & Expo Workshops, ICME Workshops, Hong Kong, China, July 10-14, 2017, pp. 613–616, IEEE Computer Society, 2017.
Accurate extrinsic calibration between monocular camera and sparse 3D Lidar points without markers Inproceedings
In: IEEE Intelligent Vehicles Symposium, IV 2017, Los Angeles, CA, USA, June 11-14, 2017, pp. 424–429, IEEE, 2017.
Deep Salient Object Detection by Integrating Multi-level Cues Inproceedings
In: 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017, Santa Rosa, CA, USA, March 24-31, 2017, pp. 1–10, IEEE Computer Society, 2017.
2016
Multi-Body Non-Rigid Structure-from-Motion Inproceedings
In: Fourth International Conference on 3D Vision, 3DV 2016, Stanford, CA, USA, October 25-28, 2016, pp. 148–156, IEEE Computer Society, 2016.
Deep Depth Super-Resolution: Learning Depth Super-Resolution Using Deep Convolutional Neural Network Inproceedings
In: Lai, Shang-Hong; Lepetit, Vincent; Nishino, Ko; Sato, Yoichi (Ed.): Computer Vision - ACCV 2016 - 13th Asian Conference on Computer Vision, Taipei, Taiwan, November 20-24, 2016, Revised Selected Papers, Part IV, pp. 360–376, Springer, 2016.
Robust Optical Flow Estimation of Double-Layer Images under Transparency or Reflection Inproceedings
In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pp. 1410–1419, IEEE Computer Society, 2016.
Rolling Shutter Camera Relative Pose: Generalized Epipolar Geometry Inproceedings
In: 2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, Las Vegas, NV, USA, June 27-30, 2016, pp. 4132–4140, IEEE Computer Society, 2016.
Simultaneous Correspondences Estimation and Non-Rigid Structure Reconstruction Inproceedings
In: 2016 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2016, Gold Coast, Australia, November 30 - December 2, 2016, pp. 1–7, IEEE, 2016.
Pushing the limit of non-rigid structure-from-motion by shape clustering Inproceedings
In: 2016 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2016, Shanghai, China, March 20-25, 2016, pp. 1999–2003, IEEE, 2016.
Reliable scale estimation and correction for monocular Visual Odometry Inproceedings
In: 2016 IEEE Intelligent Vehicles Symposium, IV 2016, Gotenburg, Sweden, June 19-22, 2016, pp. 490–495, IEEE, 2016.
2015
Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs Inproceedings
In: IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015, Boston, MA, USA, June 7-12, 2015, pp. 1119–1127, IEEE Computer Society, 2015.
Hierarchical Aggregation Based Deep Aging Feature for Age Prediction Inproceedings
In: 2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015, Adelaide, Australia, November 23-25, 2015, pp. 1–5, IEEE, 2015.
2014
A Simple Prior-Free Method for Non-rigid Structure-from-Motion Factorization Journal Article
In: Int. J. Comput. Vis., vol. 107, no. 2, pp. 101–122, 2014.