Seminar Computer Vision SS'24
Seminar

Topic: Recent research in Visual Computing

Latest News

Content

In this seminar we discuss current research results in computer vision, visual computing and image/video processing. The task of the participants is to understand and explain a certain research topic to the other participants. In a block seminar in the middle of the semester the background knowledge required for the final talks will be presented in oral presentations and at the end of the semester, the respective research topic is presented in an oral presentation. This must also be rehearsed beforehand in front of another student and his/her suggestions for improvement must be integrated.

Participants

The course is aimed at bachelor's and master's students from the fields of computer science (Informatik), IST, business informatics (Wirtschaftsinformatik), and data science.

Registration takes place centrally via StudIP. The number of participants is initially limited to 8 students, but can be extended in the kickoff if necessary.

Important Dates

All dates listed here must be adhered to. Attendance at all events is mandatory.

• 01.02. - 07.02.2024: Registration via Stud.IP
• 09.04.2024, 10:30: Kickoff Meeting (G30, ICG)
• 16.04.2024: End of the deregistration period
• 18.04.2024, 12-13 , G30 (ICG): Gather topics for fundamentals talk
• 05.05.2024: Submission of presentation slides for fundamentals talk (please use the following naming scheme: Lastname_FundamentalsPresentation_SeminarCV.pdf)
• 07.05.2024, 15:00 - 18:00, G30 (ICG): Fundamentals presentations, Block
• Till 02.06.2024: Trial presentation for final presentation (between tandem partners from fundamentals talk)
• 13.06.2024: Submission of presentation slides for final talk (ALL participants!) (please use the following naming scheme: Lastname_FinalPresentation_SeminarCV.pdf)
• 13.06.2024, 09:00 - 15:00, G30 (ICG): Presentations - Block Event Part 1
• 14.06.2024, 09:00 - 15:00, G30 (ICG): Presentations - Block Event Part 2

Registered students have the possibility to deregister until 2 weeks after the start of the lectures at the latest. For a successful deregistration it is necessary to deregister with the seminar supervisor.

The respective drop-offs are done by email to seminarcv@cg.cs.tu-bs.de , and your advisor, and if necessary by email to the tandem partner. Unless otherwise communicated, submissions must be made by 11:59pm on the submission day.

If you have any questions about the event, please contact seminarcv@cg.cs.tu-bs.de.

Format

• The topics will be distributed amongst the participants during the Kickoff event.
• The topics for the fundamentals talks will be distributed amongst the participants during the second meeting.
• The topics will be presented in approximately 20 minute presentations followed by a discussion.
• For the on-site lectures, a laptop of the institute or an own laptop can be used. If the institute laptop is to be used, it is necessary to contact seminarcv@cg.tu-bs.de in time, at least two weeks before the presentations. In this case, the presentation slides must be made available at least one week before the lecture.
• The presentations will be given on site. If, for some reason, the presentations take place online, Big Blue Button will be used as a platform. In this case, students need their own PC with microphone. In addition, a video transmission during the own lecture would be desirable. If these requirements cannot be met, it is necessary to contact seminarcv@cg.cs.tu-bs.de in time.
• The language for the presentations can be either German or English.
• The presentations are mandatory requirements to pass the course successfully.

Files and Templates

• Kickoff-Slides
• Slide-Template (optional usage)

Topics

1. Unlocking Potential: The Development and User-Friendly Evaluation of a Virtual Reality Intervention for Attention-Deficit/Hyperactivity Disorder
   (Wong et al.) Appl. Syst. Innov. 2023
   
   Attention-Deficit/Hyperactivity Disorder (ADHD) is typically first diagnosed in early childhood. Medication and cognitive behavioural therapy are considered effective in treating children with ADHD, whereas these treatments appear to have some side effects and restrictions. Virtual reality (VR), therefore, has been applied to exposure therapy for mental disorders. Previous studies have adopted VR in the cognitive behavioural treatment for children with ADHD; however, no research has used VR to develop social skills training for children with ADHD. This study aimed to develop a VR-based intervention (Social VR) to improve social skills in children with symptoms of ADHD.
   https://www.mdpi.com/2571-5577/6/6/110
   
   Advisor: Anika Jewst
   
   
2. Measuring Attentional Distraction in Children With ADHD Using Virtual Reality Technology With Eye-Tracking
   (Stokes et al.) Front. Virtual Real. 2022
   
   Distractions inordinately impair attention in children with Attention-Deficit Hyperactivity Disorder (ADHD) but examining this behavior under real-life conditions poses a challenge for researchers and clinicians. Virtual reality (VR) technologies may mitigate the limitations of traditional laboratory methods by providing a more ecologically relevant experience. The use of eye-tracking measures to assess attentional functioning in a VR context in ADHD is novel. In this proof of principle project, we evaluate the temporal dynamics of distraction via eye-tracking measures in a VR classroom setting with 20 children diagnosed with ADHD between 8 and 12 years of age.
   https://www.frontiersin.org/articles/10.3389/frvir.2022.855895/full
   
   Advisor: Anika Jewst

3. Iterative alpha-(de)Blending: a Minimalist Deterministic Diffusion Model
   (Heitz et al.) SIGGRAPH 2023
   
   In this paper the authors derive a minimalist difussion model which, while being pretty much equivalent to existing ones, is derived in a simpler manner, using only basic (bachelor-level) concepts.
   https://ggx-research.github.io/publication/2023/05/10/publication-iadb.html

   Advisor: Fabian Friederichs
   
   
4. Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
   (Blattmann et al.) CVPR 2023
   
   This paper introduces a novel method for high-resolution video synthesis using Latent Diffusion Models (LDMs). By introducing a temporal dimension to the latent space and fine tuning on video data, it achieves remarkable clarity and continuity in generated videos, setting a new state-of-the-art in the field. The paper focuses on practical applications such as simulating real-world driving scenarios, showcasing its potential for diverse and creative content creation.
   https://research.nvidia.com/labs/toronto-ai/VideoLDM/
   
   Advisor: Jannis Malte Möller
   
   
5. Towards Attention-Aware Rendering
   (Krajancich et al.) SIGGRAPH 2023
   
   Existing perceptual models used in foveated graphics neglect the effects of visual attention. We introduce the first attention-aware model of contrast sensitivity and motivate the development of future foveation models, demonstrating that tolerance for foveation is significantly higher when the user is concentrating on a task in the fovea.
   https://www.computationalimaging.org/publications/attention-aware/
   
   Advisor: Jannis Malte Möller
   
   
6. The effect of display capabilities on the gloss consistency between real and virtual objects
   (Chen et al.) SIGGRAPH Asia 2023
   
   This study examines the challenges in accurately reproducing gloss on displays. Using an advanced imaging pipeline, we achieve precise gloss matching between virtual and real objects on an augmented-reality HDR stereoscopic display. The experiments reveal that reduced luminance and dynamic range on the display diminish perceived gloss. The findings highlight the need for careful tone mapping selection for accurate gloss reproduction on low dynamic range displays.
   https://stereohdrgloss.mpi-inf.mpg.de
   
   Advisor: Steve Grogorick
   
   
7. Ultra-High Resolution SVBRDF Recovery from a Single Image
   (Guo et al.) TOG 2023
   
   The paper discusses challenges in generating Ultra-High Resolution (UHR) material maps from a single photographies. This is a challenging problem, due to limitations in computational resources and the local nature of convolutional layers. The proposed solution involves dividing a UHR image into low-resolution patches, extracting local features, and incorporating a global feature extractor with coordinate-aware modules to capture long-range dependencies. The end-to-end method aims to generate UHR Surface Reflectance Distribution Function (SVBRDF) maps from a single image, addressing both fine spatial details and consistent global structures.
   https://dl.acm.org/doi/pdf/10.1145/3593798
   
   Advisor: Fabian Friederichs
   
   
8. Delaunay Painting: Perceptual Image Colouring from Raster Contours with Gaps
   (Parakkat et al.) EG 2023
   
   The paper introduces "Delaunay Painting," a user-friendly method for coloring contour sketches with gaps. The approach utilizes Delaunay triangulation of input contours and iteratively fills triangles with appropriate colors, guided by dynamic flow values from color hints. Aesthetic refinement is achieved through energy minimization of contour curves and heuristics for sharp corners. The method efficiently handles contours with strong gaps and allows for interactive and automated coloring, demonstrating applicability in medical imaging and sketch segmentation.
   https://onlinelibrary.wiley.com/doi/10.1111/cgf.14517
   
   Advisor: Steve Grogorick
   
   

Useful Resources

Example of a good presentation (video on the website under the Presentation section, note how little text is needed, and how much has been visualized to create an intuitive understanding).

General writing tips for scientific papers (mainly intended for writing scientific articles, but also good to use for summaries).

Advisors

Anika Jewst

Fabian Friederichs

Jannis Möller

Dr. Steve Grogorick