News
Currently, no news are available
3D and 4D Computer Vision
Course Description
Computer Vision is an interdisciplinary research field at the intersection of machine learning and signal processing. It studies techniques for automatic analysis and interpretation of visual and multi-modal input data. This lecture focuses on one of the advanced subfields of Computer Vision related to the inference of the observed higher-dimensional structures (3D and deformable 3D) from lower-dimensional observations (2D images).
Our world is inherently non-rigid at different spatial and temporal scales. Reconstructing and modelling it in 4D from visual observations is a vibrant research field that remains challenging and that has numerous practical applications, for instance, in AR/VR/XR, computer game development, human-computer interaction and sport analytics. The frequent challenges of this field include the ill-posedness of the underlying optimisation problems and settings (e.g., monocular, which is of special interest in Computer Vision) and observed scene conditions (e.g., partial observations, low light or high-speed motions), among many others. The goal of the lecture "3D and 4D Computer Vision" is to introduce foundational concepts of 3D computer vision for deformable and composite scenes (4D = 3D + time) as well as results of the latest research in the field in a systematic and structured manner through generalisation of studied concepts from 3D to 4D cases.
The lecture will cover the fundamentals of 3D computer vision applicable across a wide range of 3D and 4D settings (multiple view geometry, triangulation, stereo vision, bundle adjustment, linear transformations, parametrisations of rotations), different types of visual sensors (RGB, event and depth cameras), 3D and 4D scene representations, deformation models and regularisers, non-rigid structure from motion (NRSfM), shape-from-template, correspondence problems, novel-view synthesis of non-rigid scenes, generative and diffusion models in 4D vision, 3D human pose estimation, egocentric 4D vision as well as video generation of composite scenes. Apart from milestone methods in the field, the lecture will discuss several recent works on 4D vision including state-of-the-art approaches. This lecture is accompanied by triweekly theoretical exercises.
Schedule and Other Details
Course webpage: https://4dqv.mpi-inf.mpg.de/teaching/3D_and_4D_Computer_Vision_3rd/
Workload: 6 Credit Points
Format: Weekly lectures + biweekly exercises
Time: Wednesdays: 14:15 – 15:45 p.m. (lecture) / Thursdays: 14:15 – 15:45 p.m. (exercise)
Location: Wednesdays: 002 in E1 5 / Thursdays: 024 in E 1 4
Exam: Oral
Exam admission: At least 50% of correctly accomplished exercises.
Prerequisites
The lecture "3D and 4D Computer Vision" targets students in the following programs: Visual Computing (M.Sc.), Computer Science (M.Sc.), and Data Science and Artificial Intelligence (M.Sc.).
Some background in linear algebra, calculus, image processing, computer graphics and machine learning is recommended.
Course Content
14.10.26: Introduction and Fundamentals of 3D and 4D Computer Vision I
21.10.26: Fundamentals of 3D and 4D Computer Vision II
28.10.26: No Lecture
04.11.26: Scene Representations
11.11.26: Correspondence Problems
18.11.26: Multi-View Geometry and Structure from Motion
25.11.26: Volumetric Rendering (remote)
02.12.26: General 4D Reconstruction (remote)
09.12.26: No Lecture
16.12.26: No Lecture
06.01.27: No Lecture
13.01.27: Human Pose Estimation
20.01.27: Egocentric 4D Vision
27.01.27: Generative Models
03.02.27: Event-Based Vision
10.02.27: Recap and Recent Research
17.02.27: Recent Research
Exercise Sheets and Tutorials
22.10.26: Exercise sheet 1 released
29.10.26: Tutorial 1
05.11.26: Exercise sheet 2 released
12.11.26: Tutorial 2
19.11.26: Exercise sheet 3 released
26.11.26: Tutorial 3
03.12.26: Exercise sheet 4 released
10.12.26: Tutorial 4
21.01.27: Exercise sheet 5 released
28.01.27: Tutorial 5
04.02.27: Exercise sheet 6 released
11.02.27: Tutorial 6
18.02.27: Optional Q&A session / No regular exercise