News

Correction for exercise sheet 2

Written on 12.11.26 by Gino Lanzo Hahn

Dear students,

I write to make you aware that the exercise sheet 2 has been updated after an error was noticed in one of its questions.

In particular, question 4.1 asked about a loss term that was written down differently from the original paper, potentially leading to incorrect answers.
Please… Read more

Dear students,

I write to make you aware that the exercise sheet 2 has been updated after an error was noticed in one of its questions.

In particular, question 4.1 asked about a loss term that was written down differently from the original paper, potentially leading to incorrect answers.
Please take a look and update your answer accordingly.

Written on 09.11.26 (last change on 09.11.26) by Gino Lanzo Hahn

Dear students,

the feedback and results for the first exercise sheet have been released. You can find them in the same place you used to submit your answers.

Also for future submissions, please make sure to use the provided LaTeX template. If you want to use manually written solutions, check out… Read more

Dear students,

the feedback and results for the first exercise sheet have been released. You can find them in the same place you used to submit your answers.

Also for future submissions, please make sure to use the provided LaTeX template. If you want to use manually written solutions, check out the 'Q&A Format Overview' document in the Materials to see how to insert them into the template.

Let me remind you of our upcoming events:

  • The second exercise sheet has already been released, you have up until the 18th to submit it.
  • This Thursday there'll be the Q&A session for the second exercise sheet. Don't forgot to send questions your way
  • There has been a schedule change. On the 16th of December we'll have two invided talks. The details are still getting ironed out but make sure to keep your schedules open.

First Exercise sheet and Q&A

Written on 22.10.26 (last change on 22.10.26) by Gino Lanzo Hahn

Dear students,

Welcome to the 3D and 4D Computer Vision course.
Since CMS has been down for the past day, please note these important updates:

  • Exercise Sheet 1: Released today (22.10.2026) with a deadline of 04.11.2026.
  • First Q&A Session: Scheduled for 29.10.2026 in Building E1.4, Room… Read more

Dear students,

Welcome to the 3D and 4D Computer Vision course.
Since CMS has been down for the past day, please note these important updates:

  • Exercise Sheet 1: Released today (22.10.2026) with a deadline of 04.11.2026.
  • First Q&A Session: Scheduled for 29.10.2026 in Building E1.4, Room 023.

The Q&A session will begin with a detailed rundown of the format of the tutoring encounters, followed by the actual Q&A.
I highly recommend starting on the exercise sheet now so you can email your questions to the TA.

Additionally, the slides for the first lecture are now available in the Materials section. As mentioned in class, future slides will be uploaded prior to each lecture to allow you to review the topics beforehand.

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: 023 in E 1 4

Exam: Oral 

Exam admission: At least 50% of correctly completed 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

21.10.26: Introduction and Fundamentals of 3D and 4D Computer Vision I
28.10.26: Fundamentals of 3D and 4D Computer Vision II
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
02.12.26: No Lecture
09.12.26: General 4D Reconstruction (remote)
16.12.26: Invited Talks
Holiday break
06.01.27: No Lecture
13.01.27: Human Pose Estimation (remote)
20.01.27: Egocentric 4D Vision (remote tentatively)
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 Q&A Sessions

22.10.26: Exercise sheet 1 released
29.10.26: Q&A Exercise sheet 1
05.11.26: Exercise sheet 2 released + Solutions for Exercise sheet 1 presented
12.11.26: Q&A Exercise sheet 2
19.11.26: Exercise sheet 3 released + Solutions for Exercise sheet 2 presented
26.11.26: Q&A Exercise sheet 3
10.12.26: Exercise sheet 4 released + Solutions for Exercise sheet 3 presented
17.12.26: Q&A Exercise sheet 4
Holiday break
14.01.27: Exercise sheet 5 released + Solutions for Exercise sheet 4 presented
21.01.27: Q&A Exercise sheet 5
28.01.27: Exercise sheet 6 released + Solutions for Exercise sheet 5 presented
04.02.27: Q&A Exercise sheet 6
11.02.27: Solutions for Exercise sheet 6 presented + Q&A Exam

Please refer to the course timetable for detailed session timings and assignment submission deadlines.


Privacy Policy | Legal Notice
If you encounter technical problems, please contact the administrators.