Robotics and Computer Vision Lab

Publications

International Conference
2020.07.03 13:52

Non-Local Spatial Propagation Network for Depth Completion

조회 수 54 댓글 0
Extra Form
저 자 Jinsun Park, Kyungdon Joo, Zhe Hu, Chi-Kuei Liu, In So Kweon
학 회 European Conference on Computer Vision (ECCV)
논문일시(Year) 2020
논문일시(Month) 08

In this paper, we propose a robust and efficient end-to-end non-local spatial propagation network for depth completion. The proposed network takes RGB and sparse depth images as inputs and estimates non-local neighbors and their affinities of each pixel, as well as an initial depth map with pixel-wise confidences. The initial depth prediction is then iteratively refined by its confidence and non-local spatial propagation procedure based on the predicted non-local neighbors and corresponding affinities. Unlike previous algorithms that utilize fixed-local neighbors, the proposed algorithm effectively avoids irrelevant local neighbors and concentrates on relevant non-local neighbors during propagation. In addition, we introduce a learnable affinity normalization to better learn the affinity combinations compared to conventional methods. The proposed algorithm is inherently robust to the mixed-depth problem on depth boundaries, which is one of the major issues for existing depth estimation/completion algorithms. Experimental results on indoor and outdoor datasets demonstrate that the proposed algorithm is superior to conventional algorithms in terms of depth completion accuracy and robustness to the mixed-depth problem. Our implementation is publicly available on the project page.

 

Acknowledgement :

This work was partially supported by the National Information Society Agency for construction of training data for artificial intelligence (2100-2131-305-107-19).

 


List of Articles
60. Statistical Background Subtraction Based on the Exact Per-pixel Distributions
Youngbae Hwang, Hanbyul Joo, Jun-sik Kim, In So Kweon
IAPR workshop on Machine Vision Applications (MVA) 2007 / 05
59. Stereo Matching with the Distinctive Similarity Measure
Kukjin Yoon, In So Kweon
IEEE International Conference on Computer Vision (ICCV) 2007 / 10
58. Motion Estimation using Centers of Non-Overlapping Cameras
Hyeongwoo Kim, Jun-sik Kim, In So Kweon
Proceedings of the 13th Japan-Korea Joint Workshop on Frontiers of Computer Vision (FCV) 2007 / 01
57. Visual Categorization Robust to Large Intra-Class Variations using Entropy-guided Codebook
Sungho Kim, In So Kweon
Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2007 / 04
56. Sensor noise modeling using the Skellam distribution: Application to the color edge detection
Youngbae Hwang, Jun-sik Kim, In So Kweon
IEEE International Conference on Computer Vision and Pattern Recognition (CVPR) 2007 / 06
55. Accurate Motion Estimation and High-Precision 3D Reconstruction by Sensor Fusion
Yunsu Bok, Youngbae Hwang, In So Kweon
Proceedings of the IEEE International Conference on Robotics and Automation (ICRA) 2007 / 04
54. CALOS : Camera And Laser for Odometry Sensing
Yunsu Bok, Youngbae Hwang, In So Kweon
Proceedings of the 13th Japan-Korea Joint Workshop on Frontiers of Computer Vision (FCV) 2007 / 01
53. Object Categorization Robust to Surface Markings using Entropy-guided Codebook
Sungho Kim, In So Kweon
IEEE Workshop on Applications of Computer Vision (WACV) 2007 / 02
52. Determination of Color Space for Accurate Change Detection
Youngbae Hwang, Jun-sik Kim, In So Kweon
IEEE International Conference on Image Processing (ICIP) 2006 / 10
51. Semi-metric Space: A New Approach to Treat Orthogonality and Parallelism
Jun-sik Kim, In So Kweon
Asian Conference on Computer Vision (ACCV) 2006 / 01
50. Synergistic Place and Object Recognition using Bidirectional Context Information
Sungho Kim, In So Kweon
British Machine Vision Conference (BMVC) 2006 / 09
49. Fast Separation of Reflection Components Using a Specularity-Invariant Image Representation
Kukjin Yoon, Yoojin Choi, In So Kweon
IEEE International Conference on Image Processing (ICIP) 2006 / 10
48. Estimating Intrinsic Parameters of Cameras using Two Arbitrary Rectangles
Jun-sik Kim, In So Kweon
International Conference on Pattern Recognition (ICPR) 2006 / 08
47. Multi-Modal Sequential Monte Carlo for On-Line Hierarchical Graph Structure Estimation in Model-based Scene Interpretation
Sungho Kim, In So Kweon
International Conference on Pattern Recognition (ICPR) 2006 / 08
46. Automatic Extraction of Parallel Lines in Catadioptric Images
Jean-Charles Bazin, In So Kweon
Proc. of 13th IEEE International Conference on Advanced Robotics (IEEE ICAR'07) 2007 / 08
45. Simultaneous Classification and Visual Word Selection using Entropy-based Minimum Description Length
Sungho Kim, In So Kweon
International Conference on Pattern Recognition (ICPR) 2006 / 08
44. Fast Central Catadioptric Line Extraction
Jean-Charles Bazin, Cedric Demonceaux, Pascal Vasseur
Proc. of 3rd Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA’07) 2007 / 06
43. Background Robust Object Labeling by Voting of Weight-Aggregated Local Features
Sungho Kim, Kukjin Yoon, In So Kweon
International Conference on Pattern Recognition (ICPR) 2006 / 08
42. Object Recognition using Generalized Robust Invariant Feature and Gestalt Law of Proximity and Similarity
Sungho Kim, Kukjin Yoon, In So Kweon
5th IEEE Workshop on Perceptual Organization in Computer Vision (CVPRW) 2006 / 06
41. Efficient Feature Tracking for Visual SLAM by Pairwise Constraints
Jungho Kim, Hyeongwoo Kim, In So Kweon
The 4th International Conference on Ubiquitous Robots and Ambient Intelligence(URAI) 2007 / 11
Board Pagination Prev 1 ... 8 9 10 11 12 13 14 15 16 17 Next
/ 17