Skip to content (access key 's')
Logo of Technion
Logo of CS Department

Colloquia and Seminars

To join the email distribution list of the cs colloquia, please visit the list subscription page.
Computer Science events calendar in HTTP ICS format for of Google calendars, and for Outlook.
Academic Calendar at Technion site.

Upcoming Colloquia & Seminars

  • Pixel Club: Moving Forward with StyleGAN to Real Data and New Domains
    event speaker icon
    Ron Mokady (Tel-Aviv University)
    event date icon
    Tuesday, 31.5.2022, 11:30
    event location icon
    Zoom Lecture:
    StyleGAN is already quite famous for its unremarkable image editing capabilities. Although other generative models (e.g. diffusion models) achieve comparable synthesis quality, they cannot reproduce these semantically richmanipulations. In particular, StyleGAN allows the modification of various attributes, such as hair, age, pose, expression, and make-up, while still maintaining a high level of realism. Yet, it is still challenging to leverage these traits for real data or new domains. In this talk, we discuss three main obstacles: First, how to edit real images using latent-based manipulation, i.e., inverting a real image to StyleGAN'slatent space. Second, how to employ the per-image editing over videos, which requires another dimension of realism - temporal consistency. Lastly, we explore the possibilities of training StyleGAN in new and exciting domains. Short bio: I am a Computer Science Ph.D. student at Tel-Aviv University, under the supervision of Prof. Daniel Cohen-Or and Dr. Amit H. Bermano. Previously, I spent the 2020 summer at FAIR under the supervision of Prof. Lior Wolf, and the 2021 summer at Google Research. My main research interest is machine learning applications for computer vision and graphics. In particular, I work on image and video synthesis, while also interested in disentanglement, temporal coherence, supervision reduction, and the utilization of pre-trained models.
  • CGGC Seminar: Nozzle Modification for Efficient FDM 3D Printing
    event speaker icon
    Shir Rorberg (CS, Technion)
    event date icon
    Wednesday, 8.6.2022, 10:00
    event location icon
    Taub 401
    3D printing is based on layered manufacturing, where the layers are printed consecutively in increasing height order. In Fused Depositing Modeling (FDM), the printing head may travel without extruding material between separated “islands” of the sliced layers. These travel movements increase the printing time and reduce the quality of the 3D printed part. We present an extended nozzle modification, which can be applied to off-the-shelf FDM printers, and a corresponding toolpath generation algorithm. Together, these dramatically reduce the amount of travel movement, thus improving the printing time and quality of the results. The extended nozzle allows us to print the sliced layers out of order, where part of a lower layer might be printed after a higher layer was already printed. Our toolpath generation algorithm takes advantage of this capability and generates a toolpath which maximizes the number of consecutive layers printed within the same “island” without requiring any travel movement. In addition, the algorithm optimizes the order of the printed islands, and guarantees that the generated toolpath will not cause collisions between the extended nozzle and the model. We demonstrate our approach on a collection of varied models, and show that we considerably reduce the required travel, and improve the printing time and quality compared to standard layer-bylayer printing.