Visual Computing and Artificial Intelligence Department

Advance Topics of Computer Vision and Computer Graphics
in the Age of Artificial Intelligence

Seminar – Summer Semester 2025

Organizers: Christian Theobalt, Rishabh Dabral, Lin Geng Foo and Xilong Zhou

Organization | Content | Format | Resources


VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models ArXiv 2025	HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics CVPR, 2023

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
Video Generative Models Video Diffusion Models Ho et al. NeurIPS 2022 VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models Chefer et al. ArXiv 2025
Neural Cloth Simulation HOOD: Hierarchical Graphs for Generalized Modelling of Clothing Dynamics Grigorev et al. CVPR 2023 NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory Kairanda et al. NeurIPS 2024
3D Shape Representations Occupancy Networks: Learning 3D Reconstruction in Function Space Mescheder et al. CVPR 2019 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models Zhang et al. SIGGRAPH 2023
Hand-held Objects HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video Fan et al. CVPR 2024 Reconstructing Hand-Held Objects in 3D from Images and Videos Wu et al. ArXiv 2024
Diffusion Meets Flow Matching Denoising Diffusion Probabilistic Models Ho et al. NeurIPS 2020 Flow Matching for Generative Modeling Lipman et al. ICLR 2023
Diffusion Meets Action Planning Diffusion Policy: Visuomotor Policy Learning via Action Diffusion Chi et al. RSS 2023 Unified Video Action Model Li et al. ArXiv 2025
Animatable Characters - Non-Monocular LayGA: Layered Gaussian Avatars for Animatable Clothing Transfer Lin et al. SIGGRAPH 2024 Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling Li et al. CVPR 2024
Animatable Characters - Monocular Vid2Avatar-Pro: Authentic Avatar from Videos in the Wild via Universal Prior Guo et al. CVPR 2025 Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition Guo et al. CVPR 2023
Physics Based Pose Estimation D&D: Learning human dynamics from dynamic camera Li et al. ECCV 2022 Drop: Dynamics responses from human motion prior and projective dynamics Jiang et al. SIGGRAPH Asia 2023
Wearable Pose Estimation Physical Inertial Poser (PIP) Yi et al. CVPR 2022 Estimating Body and Hand Motion in an Ego-sensed World Yi et al. ArXiv 2024
Training and Evaluation with Generated Data Scaling Laws of Synthetic Images for Model Training ... for Now Fan et al. CVPR 2024 ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object Zhang et al. CVPR 2024
Understanding the World with Generative Models Generative Models: What do they know? Do they know things? Let's find out! Du et al. CVPR 2024 ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features Helbling et al. ArXiv 2025
Accelerated 3D Gaussian Splatting Taming 3DGS: High-Quality Radiance Fields with Limited Resources Mallick et al. SIGGRAPH Asia 2024 LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS Fan et al. NeurIPS 2024
Recent advances of Novel View Synthesis Quark: Real-time, High-resolution, and General Neural View Synthesis Flynn et al. SIGGRAPH Asia 2024 LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias Jin et al. ICLR 2025
Skin Appearance Modelling Practical Appearance Model for Foundation Cosmetics Lanza et al. Eurographics 2024 A Hyperspectral Space of Skin Tones for Inverse Rendering of Biophysical Skin Properties Aliaga et al. Eurographics 2023
Relightable Gaussians from OLAT Illuminations GS3: Efficient Relighting with Triple Gaussian Splatting Bi et al. SIGGRAPH Asia 2024 BiGS: Bidirectional Primitives for Relightable 3D Gaussian Splatting Liu et al. 3DV 2025
Human Pose Generation from Text CPoser: An Optimization-after-Parsing Approach for Text-to-Pose Generation Using Large Language Models Li et al. TOG 2024 ChatPose: Chatting about 3D Human Pose Feng et al. CVPR 2024
Image Matching Done Easy: 3D Vision is solved CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion Weinzaepfel et al. NeurIPS 2022 Grounding Image Matching in 3D with MASt3R Leroy et al. ArXiv 2024
Speech-driven Character Animation Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation Zhu et al. CVPR 2023 Retrieving Semantics from the Deep: an RAG Solution for Gesture Synthesis Mughal et al. CVPR 2025
Text-driven Character Animation MoFusion: A Framework for Denoising-Diffusion-based Motion Synthesis Dabral et al. CVPR 2023 MoMask: Generative Masked Modeling of 3D Human Motions Guo et al. CVPR 2024
Temporal Decorrelation of Videos Layered Neural Atlases for Consistent Video Editing Kasten et al. SIGGRAPH Asia 2021 RAFT: Recurrent All Pairs Field Transforms for Optical Flow Teed et al. ECCV 2020
Text-to-3D face generation DreamFusion: Text-to-3D using 2D Diffusion Poole et al. ICLR 2023 Portrait3D: Text-Guided High-Quality 3D Portrait Generation Using Pyramid Representation and GANs Prior Wu et al. SIGGRAPH 2024
Egocentric 3D Human Motion Capture Egocentric Whole-Body Motion Capture with FisheyeViT and Diffusion-Based Motion Refinement Wang et al. CVPR 2024 EventEgo3D++: 3D Human Motion Capture from a Head Mounted Event Camera Millerdurai et al. CVPR 2024