Program

Confirmed Invited Speakers

8:30 – 9:00, Keynote 1, Silvia Zuffi, Towards markerless shape and motion capture of animals

9:00 – 9:30, Keynote 2, Yaron Lipman, Provably Powerful Graph Neural Networks

9:30 – 10:00, Keynote 3, Erik Bekkers, Group Equivariant CNNs beyond Roto-Translations: B-Spline CNNs on Lie Groups

10:00 – 10:30, Break

10:30 – 11:00, Oral Session (10 minutes each)

1. Auto-encoding meshes of any topology with the current-splatting and exponentiation layers, Alexandre Bône (Institut du Cerveau et de la Moelle épinière); Olivier Colliot (Institut du Cerveau et de la Moelle épinière); Stanley Durrleman (Institut du Cerveau et de la Moelle épinière)
2. Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model using Deep Non-Rigid Structure from Motion, Mihir Sahasrabudhe (CentraleSupelec); Zhixin Shu (Stony Brook University); Edward HJ Bartrum (The Alan Turing Institute); Alp Guler (Ariel AI,Imperial College London); Dimitris Samaras (Stony Brook University); Iasonas Kokkinos (Ariel AI / University College London)
3. Patch-based reconstruction of a textureless deformable 3D surface from a single RGB image, Aggeliki Tsoli (FORTH); Antonis A. Argyros (CSD-UOC and ICS-FORTH)

11:00 – 11:30, Keynote 4, Victor Lempitsky, Image-space neural surface modeling for realistic rendering

11:30 – 12:00, Keynote 5, Vladlen Koltun

Lunch Break

13:30 – 14:00, Keynote 6, Sanja Fidler

14:00 – 14:30, Keynote 7, Qixing Huang, Geometry Learning under Hybrid 3D Representations

14:30 – 15:00, Oral Session (10 minutes each)

1. Render4Completion: Synthesizing Multi-view Depth Maps for 3D Shape Completion, Tao Hu (University of Maryland); Zhizhong Han (University of Maryland, College Park); Abhinav Shrivastava (University of Maryland); Matthias Zwicker (University of Maryland)
2. Momen(e)t: Flavor the Moments in Learning to Classify Shapes, Mor Joseph-Rivlin (Technion – Israel Institute of Technology); Alon Zvirin (Technion); Ron Kimmel (Technion)
3. A Geometric Approach to Obtain a Bird's Eye View from an Image, Ammar Abbas (University of Oxford); Andrew Zisserman (University of Oxford)

15:00 – 16:00, Poster Session

16:00 – 16:30, Keynote 8, Matthias Niessner

16:30 – 17:00, Keynote 9, Georgia Gkioxari

17:00 - 17:30, Keynote 10, Daniel Cremers

Poster Presentations

The numbers are poster stand IDs:

41. A Decoder-Free Approach for Unsupervised Clustering and Manifold Learning with Random Triplet Mining, Nina, Oliver A; Moody, Jamison; Milligan, Clarissa

42. Multi-view PointNet for 3D Scene Understanding, Jaritz, Maximilian; Gu, Jiayuan; Su, Hao

43. Parametric Human Shape Reconstruction via Bidirectional Silhouette Guidance, Sun, Shuang; Li, Chen; Guo, Zhenhua; Tai, Yu-Wing

44: Auto-encoding meshes of any topology with the current-splatting and exponentiation layers, Bône, Alexandre; Colliot, Olivier; Durrleman, Stanley

45: Generalizing Monocular 3D Human Pose Estimation in the Wild, Wang, Luyang; Chen, Yan; Guo, Zhenhua; Qian, Keyuan; Lin, Mude ; Li, Hongsheng; Ren, Jimmy

46: Patch-based reconstruction of a textureless deformable 3D surface from a single RGB image, Tsoli, Aggeliki; Argyros, Antonis A.

47: Self-Supervised Learning of Depth and Motion Under Photometric Inconsistency, Shen, Tianwei; Luo, Zixin; Zhou, Lei; Yao, Yao; Li, Shiwei; Zhang, Jiahui; Fang, Tian; Quan, Long

48: Lifting AutoEncoders: Unsupervised Learning of a Fully-Disentangled 3D Morphable Model using Deep Non-Rigid Structure from Motion, Sahasrabudhe, Mihir; Shu, Zhixin; Bartrum, Edward HJ; Guler, Alp; Samaras, Dimitris; Kokkinos, Iasonas

49: Floors are Flat: Leveraging Semantics for Real-Time Surface Normal Prediction, Hickson, Steven; Essa, Irfan; Raveendran, Karthik; Murphy, Kevin; Fathi, Alireza

50: Hyperparameter-Free Losses for Model-Based Monocular Reconstruction, Ramon Maldonado, Eduard; Ruiz, Guillermo; Batard, Thomas; Giro-i-Nieto, Xavier

51: Momen(e)t: Flavor the Momentsin Learning to Classify Shapes, Joseph-Rivlin, Mor; Zvirin, Alon; Kimmel, Ron

52: A Geometric Approach to Obtain a Bird's Eye View from an Image, Abbas, Ammar; Zisserman, Andrew

53: Rethinking Task and Metrics of Instance Segmentation on 3D Point Clouds, Arase, Kosuke; Mukuta, Yusuke; Harada, Tatsuya

54: Render4Completion: Synthesizing Multi-view Depth Maps for 3D Shape Completion, Hu, Tao; Han, Zhizhong; Shrivastava, Abhinav; Zwicker, Matthias

55: Residual Attention Graph Convolutional Network for Geometric 3D Scene Classification, Mosella-Montoro, Albert; Ruiz-Hidalgo, Javier

56: Learning to Reconstruct Symmetric Shapes using Planar Parameterization of 3D Surface, Jain, Hardik; Wöllhaf, Manuel; Hellwich, Olaf

57: SpiralNet++: A Fast and Highly Efficient Mesh Convolution Operator, Gong, Shunwang ; Chen, Lei; Zafeiriou, Stefanos; Bronstein, Michael

Presenter Instructions

The oral presentation will be 10 minutes each. The presenter may use his/her own laptop. The projector in the workshop room ONLY has HDMI connection and the recommended slide format is 16:9. Please find the session chair and test your laptop before your oral session.

All the accepted papers will be presented in the poster session. The dimension of poster panels is the same as that of the main conference: http://iccv2019.thecvf.com/submission/presentation