Visual Computing

Headed by Rudolf Mößbauer Tenure Track Professor Matthias Nießner, the Visual Computing Lab at TUM is a group of research enthusiasts pushing the state of the art at the intersection of computer vision, computer graphics, and machine learning.

This Focus Group works on the creation and detection of synthetic media, also known as deepfakes. We have already built a large data set of videos that includes different types of face manipulation (FaceForensics++), and we have used it to train effective tools based on deep learning to distinguish between real and fake content. We have also devised few-shot learning strategies to handle scenarios where only a handful of fake examples are available during training. Currently, we are following innovative identity-based approaches where we look at the problem from a different perspective, by focusing on the facial characteristics of a specific identity. We can then reformulate the problem as an authentication task: Is this the person it is claimed to be? Within this framework, we rely not only on classic features based on the biometrics of a specific subject, but also on new features based on emotions. Moreover, we are developing a multimodal approach that relies on both the video and the audio signals. This new approach will help in enhancing generalization with respect to new forms of manipulation and in improving detection performance in realistic scenarios.

For a very successful example of the work of the Visual Computing group, see their project Face2Face – Real-time Face Capture and Reenactment of RGB Videos.

Since 2018, Hans Fischer Senior Fellow Prof. Leonidas Guibas (Stanford University) and Hans Fischer Fellow Dr. Angel Xuan Chang (Eloquent Labs, Simon Fraser University) have joined the Focus Group, followed by Hans Fischer Senior Fellow Prof. Luisa Verdoliva (University of Federico II, Naples) in 2020.
 

TUM-IAS funded doctoral candidates:
Armen Avetisyan, Visual Computing, TUM
Ji Hou, Visual Computing, TUM
Andreas Rössler, Visual Computing, TUM

Publications by the Focus Group

2021

  • Burov, Andrei; Nießner, Matthias; Thies, Justus: Dynamic Surface Function Networks for Clothed Human Bodies. , 2021 more…
  • Chen, Dave Zhenyu; Wu, Qirui; Nießner, Matthias; Chang, Angel X.: D3Net: A Speaker-Listener Architecture for Semi-supervised Dense Captioning and Visual Grounding in RGB-D Scans. , 2021 more…
  • Cozzolino, Davide; Rössler, Andreas; Thies, Justus; Nießner, Matthias; Verdoliva, Luisa: ID-Reveal: Identity-aware DeepFake Video Detection. 2021 more…
  • Cozzolino, Davide; Thies, Justus; Rössler, Andreas; Nießner, Matthias; Verdoliva, Luisa: SpoC: Spoofing Camera Fingerprints. 2021 more…
  • Dahnert, Manuel; Hou, Ji; Nießner, Matthias; Dai, Angela: Panoptic 3D Scene Reconstruction From a Single RGB Image. , 2021 more…
  • Gojcic, Zan; Litany, Or; Wieser, Andreas; Guibas, Leonidas J.; Birdal, Tolga: Weakly Supervised Learning of Rigid 3D Scene Flow. , 2021 more…
  • Hou, Ji; Xie, Saining; Graham, Benjamin; Dai, Angela; Nießner, Matthias: Pri3D: Can 3D Priors Help 2D Representation Learning? , 2021 more…
  • Huang, Jiahui; Wang, He; Birdal, Tolga; Sung, Minhyuk; Arrigoni, Federica; Hu, Shi-Min; Guibas, Leonidas: MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization. , 2021 more…
  • Mo, Kaichun; Qin, Yuzhe; Xiang, Fanbo; Su, Hao; Guibas, Leonidas: O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning. , 2021 more…
  • Weng, Yijia; Wang, He; Zhou, Qiang; Qin, Yuzhe; Duan, Yueqi; Fan, Qingnan; Chen, Baoquan; Su, Hao; Guibas, Leonidas J.: CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point Clouds. , 2021 more…

2020

  • Božič, Aljaž; Palafox, Pablo; Zollhöfer, Michael; Thies, Justus; Dai, Angela; Nießner, Matthias: Neural Deformation Graphs for Globally-consistent Non-rigid Reconstruction. , 2020 more…
  • Chen, Dave Zhenyu; Chang, Angel X.; Nießner, Matthias: ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language. 2020 more…
  • Chen, Dave Zhenyu; Gholami, Ali; Nießner, Matthias; Chang, Angel X.: Scan2Cap: Context-aware Dense Captioning in RGB-D Scans. 2020 more…
  • Chen, Dave Zhenyu; Gholami, Ali; Nießner, Matthias; Chang, Angel X.: Scan2Cap: Context-aware Dense Captioning in RGB-D Scans. , 2020 more…
  • Dai, Angela; Siddiqui, Yawar; Thies, Justus; Valentin, Julien; Nießner, Matthias: SPSG: Self-Supervised Photometric Scene Generation from RGB-D Scans. , 2020 more…
  • Dong, Siyan; Fan, Qingnan; Wang, He; Shi, Ji; Yi, Li; Funkhouser, Thomas; Chen, Baoquan; Guibas, Leonidas: Robust Neural Routing Through Space Partitions for Camera Relocalization in Dynamic Indoor Environments. , 2020 more…
  • Hou, Ji; Graham, Benjamin; Nießner, Matthias; Xie, Saining: Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts. , 2020 more…
  • Huang, Jingwei; Thies, Justus; Dai, Angela; Kundu, Abhijit; Jiang, Chiyu Max; Guibas, Leonidas; Nießner, Matthias; Funkhouser, Thomas: Adversarial Texture Optimization from RGB-D Scans. 2020 more…
  • Qi, Charles R.; Chen, Xinlei; Litany, Or; Guibas, Leonidas J.: ImVoteNet: Boosting 3D Object Detection in Point Clouds with Image Votes. 2020 more…
  • Wang, He; Cong, Yezhen; Litany, Or; Gao, Yue; Guibas, Leonidas J.: 3DIoUMatch: Leveraging IoU Prediction for Semi-Supervised 3D Object Detection. , 2020 more…
  • Xiaolong Li, He Wang, Li Yi, Leonidas J. Guibas, A. Lynn Abbott, Shuran Song: Category-Level Articulated Object Pose Estimation. CVPR 2020, 2020, 3703-3712 more…

2019

  • Andreas Rössler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, Matthias Nießner: FaceForensics++: Learning to Detect Manipulated Facial Images. 2019 more…
  • Angela Dai, Christian Diller, Matthias Nießner: SG-NN: Sparse Generative Neural Networks for Self-Supervised Scene Completion of RGB-D Scans. 2019 more…
  • Armen Avetisyan, Angela Dai, Matthias Nießner: End-to-End CAD Model Retrieval and 9DoF Alignment in 3D Scans. 2019 more…
  • Chiyu "Max" Jiang, Dana Lynn Ona Lansigan, Philip Marcus, Matthias Nießner: DDSL: Deep Differentiable Simplex Layer for Learning Geometric Signals. 2019 more…
  • Chiyu "Max" Jiang, Dequan Wang, Jingwei Huang, Philip Marcus, Matthias Nießner: Convolutional Neural Networks on non-uniform geometrical signals using Euclidean spectral transformation. 2019 more…
  • Chiyu "Max" Jiang, Jingwei Huang, Karthik Kashinath, Prabhat, Philip Marcus, Matthias Niessner: Spherical CNNs on Unstructured Grids. 2019 more…
  • Dahnert, Manuel; Dai, Angela; Guibas, Leonidas; Nießner, Matthias: Joint Embedding of 3D Scan and CAD Objects. 2019 more…
  • Davide Cozzolino, Justus Thies, Andreas Rössler, Matthias Nießner, Luisa Verdoliva: SpoC: Spoofing Camera Fingerprints. 2019 more…
  • Dejan Azinović, Tzu-Mao Li, Anton Kaplanyan, Matthias Nießner: Inverse Path Tracing for Joint Material and Lighting Estimation. 2019 more…
  • Dong, Siyan; Xu, Kai; Zhou, Qiang; Tagliasacchi, Andrea; Xin, Shiqing; Nießner, Matthias; Chen, Baoquan: Multi-robot collaborative dense scene reconstruction. ACM Transactions on Graphics 38 (4), 2019, 1-16 more…
  • He Wang, Srinath Sridhar, Jingwei Huang, Julien Valentin, Shuran Song, Leonidas J. Guibas: Normalized Object Coordinate Space for Category-Level 6D Object Pose and Size Estimation. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, 2019, pp. 2642-2651 more…
  • Ji Hou, Angela Dai, Matthias Nießner: 3D-SIC: 3D Semantic Instance Completion for RGB-D Scans. 2019 more…
  • Jingwei Huang, Haotian Zhang, Li Yi, Thomas Funkhouser, Matthias Niessner, Leonidas J. Guibas: TextureNet: Consistent Local Parametrizations for Learning From High-Resolution Signals on Meshes. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019, 2019, pp. 4440-4449 more…
  • Johanna Wald, Armen Avetisyan, Nassir Navab, Federico Tombari, Matthias Nießner: RIO: 3D Object Instance Re-Localization in Changing Indoor Environments. 2019 more…
  • Justus Thies, Michael Zollhöfer, Matthias Nießner: Deferred Neural Rendering: Image Synthesis using Neural Textures. 2019 more…
  • Manuel Dahnert, Angela Dai, Leonidas Guibas, Matthias Nießner: Joint Embedding of 3D Scan and CAD Objects. 2019 more…
  • Qi, Charles R.; Litany, Or; He, Kaiming; Guibas, Leonidas J.: Deep Hough Voting for 3D Object Detection in Point Clouds. 2019 more…
  • Yawar Siddiqui, Julien Valentin, Matthias Nießner: ViewAL: Active Learning with Viewpoint Entropy for Semantic Segmentation. 2019 more…

2018

  • Angela Dai, Matthias Nießner: Scan2Mesh: From Unstructured Range Scans to 3D Meshes. 2018 more…
  • Armen Avetisyan, Manuel Dahnert, Angela Dai, Manolis Savva, Angel X. Chang, Matthias Nießner: Scan2CAD: Learning CAD Model Alignment in RGB-D Scans. 2018 more…
  • Avetisyan, Armen; Dahnert, Manuel; Dai, Angela; Savva, Manolis; Chang, Angel X.; Nießner, Matthias: Scan2CAD: Learning CAD Model Alignment in RGB-D Scans. 2018 more…
  • Dai, Angela; Nießner, Matthias: 3DMV: Joint 3D-Multi-view Prediction for 3D Semantic Scene Segmentation. In: Computer Vision – ECCV 2018. Springer International Publishing, 2018 more…
  • Dai, Angela; Ritchie, Daniel; Bokeloh, Martin; Reed, Scott; Sturm, Jurgen; Niessner, Matthias: ScanComplete: Large-Scale Scene Completion and Semantic Segmentation for 3D Scans. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, IEEE, 2018 more…
  • Fang, Xianzhong; Bao, Hujun; Tong, Yiying; Desbrun, Mathieu; Huang, Jin: Quadrangulation through morse-parameterization hybridization. ACM Transactions on Graphics 37 (4), 2018, 1-15 more…
  • Ganapathi-Subramanian, Vignesh; Diamanti, Olga; Pirk, Soeren; Tang, Chengcheng; Niessner, Matthias; Guibas, Leonidas: Parsing Geometry Using Structure-Aware Shape Templates. 2018 International Conference on 3D Vision (3DV), IEEE, 2018 more…
  • Hepp, Benjamin; Nießner, Matthias; Hilliges, Otmar: Plan3D. ACM Transactions on Graphics 38 (1), 2018, 1-17 more…
  • Jan Svoboda, Jonathan Masci, Federico Monti, Michael M. Bronstein, Leonidas Guibas: PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks. Proceedings of the International Conference on Learning Representations, 2018 more…
  • Ji Hou, Angela Dai, Matthias Nießner: 3D-SIS: 3D Semantic Instance Segmentation of RGB-D Scans. 2018 more…
  • Jingwei Huang, Haotian Zhang, Li Yi, Thomas Funkhouser, Matthias Nießner, Leonidas Guibas: TextureNet: Consistent Local Parametrizations for Learning from High-Resolution Signals on Meshes. 2018 more…
  • Kaichun Mo, Shilin Zhu, Angel X. Chang, Li Yi, Subarna Tripathi, Leonidas J. Guibas, Hao Su: PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding. 2018 more…
  • Kaichun Mo, Shilin Zhu, Angel X. Chang, Li Yi, Subarna Tripathi, Leonidas J. Guibas, Hao Su: PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding. 2018 more…
  • Kim, Hyeongwoo; Theobalt, Christian; Carrido, Pablo; Tewari, Ayush; Xu, Weipeng; Thies, Justus; Niessner, Matthias; Pérez, Patrick; Richardt, Christian; Zollhöfer, Michael: Deep video portraits. ACM Transactions on Graphics 37 (4), 2018, 1-14 more…
  • Mo, Kaichun; Zhu, Shilin; Chang, Angel X.; Yi, Li; Tripathi, Subarna; Guibas, Leonidas J.; Su, Hao: PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding. 2018 more…
  • Shi, Yifei; Xu, Kai; Nießner, Matthias; Rusinkiewicz, Szymon; Funkhouser, Thomas: PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction. In: Computer Vision – ECCV 2018. Springer International Publishing, 2018 more…
  • Thies, Justus; Zollhöfer, Michael; Stamminger, Marc; Theobalt, Christian; Nießner, Matthias: FaceVR. ACM Transactions on Graphics 37 (2), 2018, 1-15 more…
  • Thies, Justus; Zollhöfer, Michael; Stamminger, Marc; Theobalt, Christian; Nießner, Matthias: Face2Face. Communications of the ACM 62 (1), 2018, 96-104 more…
  • Thies, Justus; Zollhöfer, Michael; Theobalt, Christian; Stamminger, Marc; Niessner, Matthias: Headon. ACM Transactions on Graphics 37 (4), 2018, 1-13 more…
  • Vincent Sitzmann, Justus Thies, Felix Heide, Matthias Nießner, Gordon Wetzstein, Michael Zollhöfer: DeepVoxels: Learning Persistent 3D Feature Embeddings. 2018 more…
  • Yi, Li; Zhao, Wang; Wang, He; Sung, Minhyuk; Guibas, Leonidas: GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud. 2018 more…
  • Zollhöfer, M.; Thies, J.; Garrido, P.; Bradley, D.; Beeler, T.; Pérez, P.; Stamminger, M.; Nießner, M.; Theobalt, C.: State of the Art on Monocular 3D Face Reconstruction, Tracking, and Applications. Computer Graphics Forum 37 (2), 2018, 523-550 more…
  • Zollhöfer, Michael; Stotko, Patrick; Görlitz, Andreas; Theobalt, Christian; Nießner, Matthias; Klein, Reinhard; Kolb, Andreas: State of the Art on 3D Reconstruction with RGB-D Cameras. Computer Graphics Forum 37 (2), 2018, 625-652 more…