Picture for Mathieu Salzmann

Mathieu Salzmann

Self-supervised Segmentation via Background Inpainting

Nov 11, 2020
Isinsu Katircioglu, Helge Rhodin, Victor Constantin, Jörg Spörri, Mathieu Salzmann, Pascal Fua

Figure 1 for Self-supervised Segmentation via Background Inpainting

Figure 2 for Self-supervised Segmentation via Background Inpainting

Figure 3 for Self-supervised Segmentation via Background Inpainting

Figure 4 for Self-supervised Segmentation via Background Inpainting

* arXiv admin note: text overlap with arXiv:1907.08051

Access Paper or Ask Questions

Better Patch Stitching for Parametric Surface Reconstruction

Oct 14, 2020
Zhantao Deng, Jan Bednařík, Mathieu Salzmann, Pascal Fua

Figure 1 for Better Patch Stitching for Parametric Surface Reconstruction

Figure 2 for Better Patch Stitching for Parametric Surface Reconstruction

Figure 3 for Better Patch Stitching for Parametric Surface Reconstruction

Figure 4 for Better Patch Stitching for Parametric Surface Reconstruction

* Accepted to 3DV 2020

Access Paper or Ask Questions

Motion Prediction Using Temporal Inception Module

Oct 06, 2020
Tim Lebailly, Sena Kiciroglu, Mathieu Salzmann, Pascal Fua, Wei Wang

Figure 1 for Motion Prediction Using Temporal Inception Module

Figure 2 for Motion Prediction Using Temporal Inception Module

Figure 3 for Motion Prediction Using Temporal Inception Module

Figure 4 for Motion Prediction Using Temporal Inception Module

* 16 pages, 4 figures. To appear in the proceedings of the 15th Asian Conference on Computer Vision, ACCV 2020

Access Paper or Ask Questions

History Repeats Itself: Human Motion Prediction via Motion Attention

Jul 23, 2020
Wei Mao, Miaomiao Liu, Mathieu Salzmann

Figure 1 for History Repeats Itself: Human Motion Prediction via Motion Attention

Figure 2 for History Repeats Itself: Human Motion Prediction via Motion Attention

Figure 3 for History Repeats Itself: Human Motion Prediction via Motion Attention

Figure 4 for History Repeats Itself: Human Motion Prediction via Motion Attention

* Accepted by ECCV2020

Access Paper or Ask Questions

GarNet++: Improving Fast and Accurate Static3D Cloth Draping by Curvature Loss

Jul 20, 2020
Erhan Gundogdu, Victor Constantin, Shaifali Parashar, Amrollah Seifoddini, Minh Dang, Mathieu Salzmann, Pascal Fua

Figure 1 for GarNet++: Improving Fast and Accurate Static3D Cloth Draping by Curvature Loss

Figure 2 for GarNet++: Improving Fast and Accurate Static3D Cloth Draping by Curvature Loss

Figure 3 for GarNet++: Improving Fast and Accurate Static3D Cloth Draping by Curvature Loss

Figure 4 for GarNet++: Improving Fast and Accurate Static3D Cloth Draping by Curvature Loss

* Accepted to be published in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), July 2020. arXiv admin note: text overlap with arXiv:1811.10983

Access Paper or Ask Questions

Volumetric Transformer Networks

Jul 18, 2020
Seungryong Kim, Sabine Süsstrunk, Mathieu Salzmann

Figure 1 for Volumetric Transformer Networks

Figure 2 for Volumetric Transformer Networks

Figure 3 for Volumetric Transformer Networks

Figure 4 for Volumetric Transformer Networks

* ECCV 2020

Access Paper or Ask Questions

Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features

Jun 10, 2020
Krishna Kanth Nakka, Mathieu Salzmann

Figure 1 for Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features

Figure 2 for Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features

Figure 3 for Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features

Figure 4 for Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features

Access Paper or Ask Questions