Computer Graphics Laboratory ETH Zurich


Seminar on Digital Humans - AS 22


Course Topics

This seminar covers advanced topic in digital humans with a focus on the latest research results. Topics include estimating human pose and motion from images, human motion synthesis, learning-based human avatar creation, learning neural implicit representations for humans, modeling, animations, artificial intelligence for digital characters, and others. A collection of research papers is selected.

Course Setup

Every participant has to present one of the papers presented in the first session. Additionally, you are required to read the paper that is presented in class beforehand and participate in a discussion during the seminar. An assistant will provide support when preparing the slides and in case technical questions arise.

Learning Objectives

The goal is to get an overview of actual research topics in the field of digital humans and to improve presentation and critical analysis skills.



Presence is mandatory to pass the seminar. If a student cannot attend a seminar session, the reason (e.g. medical certificate) has to be given before the session and must be accepted by one of the organizers. More than three missed seminar sessions will cause the student to fail this class. The dates for the presentations cannot be moved.


The presentation of the selected paper contributes 75% to the final grade. Additionally, the students are required to submit a short abstract of each paper before the class (5%) as well as to lead the discussion of another paper (20%).


Number 263-5702-00L
Lecturers M. Gross, B. Solenthaler, S. Tang, R. Wampfler
Location HG E 22, Thursdays 16:15-18:00



Date Topic Paper Presenter Discussion Supervisor
29.09Invited SpeakerMoRF: Morphable Radiance Fields for Multiview Neural Head ModelingDr. Paulo Gotardo
06.103D ReconstructionHuman Mesh Recovery from Multiple ShotsAhmet ÖzüdogruSteffen VanSiwei Zhang
13.10Neural RenderingKeypointNeRF: Generalizing Image-based Volumetric Avatars using Relative Spatial Encoding of KeypointsDaphné MayorAhmet ÖzüdogruMarko Mihajlovic
20.10AnimationCharacter Controllers Using Motion VAEsXia LiSelin BarashYan Zhang
27.10Neural RenderingHumanNeRF: Free-viewpoint Rendering of Moving People from Monocular VideoJana HeimXia LiShaofei Wang
03.11Hand-Object InteractionGrasp'D: Differentiable Contact-rich Grasp Synthesis for Multi-fingered HandsMatthias KarstJennifer SchürchKorrawe Karunratanakul
10.11Deep Shape ModellingSemantic Deep Face ModelsJennifer SchürchMatthias KarstPrashanth Chandran
17.11Differentiable MusclesImplicit Neural Representation for Physics-driven Actuated Soft BodiesThomas PoyetTianfu WangLingchen Yang
24.11AnimationSoftSMPL: Data-driven Modeling of Nonlinear Soft-tissue Dynamics for Parametric HumansTianfu WangYingyan XuYuxiao Zhou
01.12AnimationAudio-Driven Facial Animation by Joint End-to-End Learning of Pose and EmotionLucas TeissierThomas PoyetPhiline Witzig
08.12Natural Language ProcessingDeveloping a Personality Model for Speech-based Conversational Agents Using the Psycholexical ApproachSteffen VanJana HeimNikola Kovacevic
15.12AnimationDeepPhase: Periodic Autoencoders for Learning Motion Phase ManifoldsYingyan XuDaphné MayorPhiline Witzig
22.12NLP / Neural RenderingText2Human: Text-Driven Controllable Human Image GenerationSelin BarashLucas TeissierLucas Relic