Logos of the MPI Informatik and the Graphics, Vision and Video group

Computer Vision and Machine Learning
for Computer Graphics

Seminar – Summer Semester 2021

Organizers: Christian Theobalt, Mohamed Elgharib, Vladislav Golyanik

Organisation | Topics | Format | Format (Detail) | Resources


A Style-Based Generator Architecture for Generative Adversarial Networks (CVPR, 2019)	Robust Motion In-betweening (SIGGRAPH, 2020)

Overview

Computer Vision strives to develop algorithms for understanding, interpreting and reconstructing information about real-world scenes from image and video data.

Computer Graphics focuses on image synthesis – algorithms to build and edit static and dynamic virtual worlds and to display them in photorealistic or stylised ways.

In recent years, these fields have converged more and more since both disciplines create and exploit models describing the visual appearance of objects and scenes. In this seminar series, we will cover advanced research topics that cross the boundaries between the fields of computer vision and computer graphics. We will concentrate on recent research results that were published at top-tier conferences and journals. This seminar will cover research papers from the following topics:

video generation and manipulation,
multi-view geometry and reconstruction,
computational photography and videography,
deep learning for computer vision and computer graphics,
multimodal video processing,
hands, body and faces: a computer perspective.

Topics

The following table lists more topics than available weeks – this is to allow some flexibility for the interests of the group to change the course structure. Once every participant has submitted their choice of topics, this list will be updated to show the presenter of each topic.

Click on each topic to show the papers to be discussed or show all papers hide all papers.

Topic and Papers	Presentation
Plausible 3D Motion Generation Learn to Dance with AIST++: Music Conditioned 3D Dance Generation Li et al. arXiv 2021 Robust Motion In-betweening Harvey et al. SIGGRAPH 2020	22 April 2021 Presenter: Shailesh Mishra Supervisor: Soshi Shimada
Foundational Works of Current 3D Graphics Research DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation Park et al. CVPR 2019 NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis Mildenhall et al. ECCV 2020	29 April 2021 Presenter: Kartik Teotia Supervisor: Yue Jiang
Regressing General 3D Shapes from RGB Images With Very Few Assumptions Shape and Viewpoint Without Keypoints Goel et al. ECCV 2020 Unsupervised Learning of Probably Symmetric Deformable 3D Objects from Images in the Wild Wu et al. CVPR 2020	6 May 2021 Presenter: Joshgun Guliyev Supervisor: Edgar Tretschk
Deep Learning Meets Multiview Geometry: Multiview Pose Estimation Learnable Triangulation of Human Pose Iskakov et al. ICCV 2019 Epipolar Transformers He et al. CVPR 2020	20 May 2021 Presenter: Nikhil Paliwal Supervisor: Jian Wang
Rigging and Skinning RigNet: Neural Rigging for Articulated Characters Xu et al. SIGGRAPH, 2020 Skinning with Dual Quaternions Kavan et al. I3D, 2007	27 May 2021 Presenter: Zhouyingcheng Liao Supervisor: Marc Habermann
People in Clothing Reconstruction TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style Patel et al. CVPR 2020 Combining Implicit Function Learning and Parametric Models for 3D Human Reconstruction Bhatnagar et al. ECCV 2020	10 June 2021 Presenter: CVMLCG Team: Short Paper Presentations Supervisor: Lingjie Liu
3D Reconstruction of Human and Hand with Interactions Three-dimensional Reconstruction of Human Interactions Fieraru et al. CVPR 2020 Reconstructing Hand-Object Interactions in the Wild Cao et al. arXiv 2020	17 June 2021 Presenter: Xianghui Xie Supervisor: Jiayi Wang
GAN meets 3D Image GANs meet Differentiable Rendering for Inverse Graphics and Interpretable 3D Neural Rendering Zhang et al. ICLR 2021 A Style-Based Generator Architecture for Generative Adversarial Networks Karras et al. CVPR 2019	24 June 2021 Presenter: Keyne Oei Supervisor: Ayush Tewari
GANs through space and time A Good Image Generator is What You Need for High-Resolution Video Synthesis Tian et al. ICLR 2021 Playable Video Generation Menapace et al arXiv 2021	1 July 2021 Presenter: Christen Millerdurai Supervisor: Gereon Fox
Conditional Multimodal Image Generation Toward Multimodal Image-to-Image Translation Zhu et al. NIPS 2017 Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis Mao et al. CVPR 2019	8 July 2021 Presenter: Arpit Jadon Supervisor: Mengyu Chu
Unsupervised Learning of Keypoints Unsupervised Learning of Object Landmarks through Conditional Image Generation Jakab et al. NeurIPS 2018 Unsupervised Learning of Category-Specific Symmetric 3D Keypoints from Point Sets Fernandez-Labrador et al. ECCV 2020	15 July 2021 Presenter: Akshay Dodwadmath Supervisor: Mallikarjun B R
Human Performance Capture Fusion4D: Real-time Performance Capture of Challenging Scenes Dou et al. SIGGRAPH 2016 DeepCap: Monocular Human Performance Capture Using Weak Supervision Habermann et al. CVPR 2020	-
Learning to Generate a Program That Describes a Scene Learning to Infer Graphics Programs from Hand-Drawn Images Ellis et al. NeurIPS 2018 Learning to Infer and Execute 3D Shape Programs Tian et al. ICLR 2019	-
Portrait NeRFs Portrait Neural Radiance Fields from a Single Image Gao et al. arXiv 2020 Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction Gafni et al. arXiv 2020	-
Total Capture: Estimating Hands, Face and Body from a Single View Monocular Expressive Body Regression through Body-Driven Attention Choutas et al. ECCV 2020 Monocular Real-time Full Body Capture with Inter-part Correlations Zhou et al. arXiv 2020	-
Quantum Computer Vision Methods Quantum-soft QUBO Suppression for Accurate Object Detection Li and Ghosh ECCV 2020 Quantum Permutation Synchronization Birdal et al. arXiv 2021	-
Videorealistic Communication Egocentric Videoconferencing Elgharib & Mendiratta et al. SIGGRAPH (Asia) 2020 Neural Voice Puppetry: Audio-driven Facial Reenactment Thies et al. ECCV 2020	-
Differentiable Rendering Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning Liu et al. ICCV 2019 Differentiable Monte Carlo Ray Tracing through Edge Sampling Li et al. SIGGRAPH (Asia) 2018	-
3D character motion synthesis Neural State Machine for Character-Scene Interactions Starke et al. SIGGRAPH (Asia) 2019 CARL: Controllable Agent with Reinforcement Learning for Quadruped Locomotion Luo et al. SIGGRAPH 2020	-
Controllable generative models Rewriting a Deep Generative Model Bau et al. ECCV 2020 Style-Controllable Speech-Driven Gesture Synthesis Using Normalising Flows Alexanderson et al. Eurographics 2020	-
Photometric Loss for Hand Pose Estimation Leveraging Photometric Consistency over Time for Sparsely Supervised Hand-Object Reconstruction Hasson et al. CVPR 2020 HTML: A Parametric Hand Texture Model for 3D Hand Reconstruction and Personalization Qian et al. ECCV 2020	-
Domain Adaptation via Neural Synthesized Images GANerated Hands for Real-Time 3D Hand Tracking from Monocular RGB Mueller et al. CVPR 2018 Weakly-supervised Domain Adaptation via GAN and Mesh Model for Estimating 3D Hand Poses Interacting Objects Baek et al. CVPR 2020	-
Acceleration for Rendering of Neural Implicit Fields Neural Sparse Voxel Fields Liu et al. NeurIPS 2020 Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Surfaces Takikawa et al. arXiv 2020	-
Neural Rendering of Humans from monocular image First Order Motion Model for Image Animation Siarohin et al. NeurIPS 2019 Neural Re-Rendering of Humans from a Single Image Sarkar et al. ECCV 2020	-

Computer Vision and Machine Learning for Computer Graphics