Visual Computing and Artificial Intelligence Department

Computer Vision and Machine Learning
for Computer Graphics

Seminar – Summer Semester 2023

Organizers: Christian Theobalt, Vladislav Golyanik, Mohamed Elgharib

Organization | Content | Format | Resources


UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture ECCV, 2022	SNUG: Self-Supervised Neural Dynamic Garments CVPR, 2022

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 stylized ways.

Machine Learning is concerned with studying and developing algorithms which use statistical models to solve problems by analyzing and drawing inference from data.

In recent years, these fields have converged more and more. Both Computer Vision and Computer Graphics create and exploit models describing the visual appearance of objects and scenes, while the most successful models heavily utilize ideas from Machine Learning. In this seminar series, we will cover advanced research topics that cross the boundaries between the fields of Computer Vision, Computer Graphics, and Machine Learning. This seminar will cover research papers from the following topics:

image and video generation, manipulation, and analysis,
multi-view geometry and reconstruction,
computational photography and videography,
shape matching,
pose estimation, tracking, and character animation,
deep learning for computer vision and computer graphics.

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. Send us an email if you cannot access a paper for some reason.

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

Topic and Papers	Presentation
3D Human Object Interaction What's in your hands? 3D Reconstruction of Generic Objects in Hands Ye et al. CVPR 2022 Reconstructing Hand-Held Objects from Monocular Video Huang et al. SIGGRAPH Asia 2022	Date: 27.04.2023 Presenter: Xiaojie Supervisor: Rishabh
Fast Radiance Field Instant Neural Graphics Primitives with a Multiresolution Hash Encoding Müller et al. ACM ToG 2022 TensoRF: Tensorial Radiance Fields Chen and Xu et al. ECCV 2022	Date: 04.05.2023 Presenter: Parham Supervisor: Guoxing
Neural Point Based Graphics Neural Point Based Graphics Aliev et al. ECCV 2020 Point-Nerf: Point-Based Neural Radiance Fields Xu et al. CVOR 2022	Date: 11.05.2023 Presenter: Ayce Supervisor: Elie
Egocentric 3D Human Pose Estimation Estimating Egocentric 3D Human Pose in Global Space Wang et al. ICCV 2021 UnrealEgo: A New Dataset for Robust Egocentric 3D Human Motion Capture Akada et al. ECCV 2022	Date: 25.05.2023 Presenter: Vedant Supervisor: Hiroyasu
Diffusion Models for 3D Generation DreamFusion: Text-to-3d using 2D diffusion Poole et al. arXiv 2022 LION: Latent Point Diffusion for 3D Shape Generation Zeng et al. NeurIPS 2022	Date: 01.06.2023 Presenter: Qinyuan Supervisor: Adam
Photorealistic Animatable Avatars Real-time Deep Dynamic Characters Habermann et al. ACM ToG 2021 Dressing Avatars: Deep Photorealistic Appearance for Physically Simulated Clothing Xiang et al. arXiv 2022	Date: 09.06.2023 Presenter: Mohamed Ovais Supervisor: Navami
Relighting Humans from Monocular Videos Relighting4D: Neural Relightable Human from Videos Chen and Liu ECCV 2022 RANA: Relightable Articulated Neural Avatars Iqbal et al. arXiv 2022	Date: 15.06.2023 Presenter: Celine Supervisor: Pulkit
Text to 3D Generation Zero-Shot Text-Guided Object Generation with Dream Fields Jain et al. CVPR 2022 Magic3D: High-Resolution Text-to-3D Content Creation Lin et al. arXiv 2022	Date: 22.06.2023 Presenter: Andria Supervisor: Mohit
Neural Photometric Stereo S3-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint Yang et al. NeurIPS 2022 PS-NeRF: Neural Inverse Rendering for Multi-view Photometric Stereo Yang et al. ECCV 2022	Date: 29.06.2023 Presenter: Shreyas Supervisor: Pulkit
Neural Acoustic Models Learning Neural Acoustic Fields Luo et al. NeurIPS 2022 SoundNeRirF: Receiver-to-Receiver Sound Neural Room Impulse Response Field He et al. OpenReview, 2023	Date: 06.07.2023 Presenter: Chinmay Supervisor: Rishabh
3D Clothed Human Reconstruction 3D Clothed Human Reconstruction in the Wild Moon et al. ECCV 2022 ICON: Implicit Clothed humans Obtained from Normals Xiu et al. CVPR 2022	Date: 13.07.2023 Presenter: Amala Supervisor: Jian
Controllable Image Synthesis StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis Sauer et al. arXiv 2023 QC-StyleGAN - Quality Controllable Image Generation and Manipulation Nguyen et al. NeurIPS 2022	Date: 20.07.2023 Presenter: Theophilus Supervisor: Pramod