When and where
Weekly on Thursdays – 11:15@ZKK.
Sessions will take place in person in our ZKK conference room unless stated otherwise and will be 45 min max.
If you want to join online or have proposals for future topics, please contact Lisa Magdalena Weijler or Irene Ballester Campos.
Next meeting
- 01.08.2024 – 11:15 am. EgoLifter: Open-world 3D Segmentation for Egocentric Perception (Wiktor) [regular time]
Future dates
- 08.08.2024
- 15.08.2024 – No 3D PC [bank holiday]
- 22.08.2024
- 29.08.2024
- 05.09.2024
Past dates
Papers and topics discussed in the past are summarized here.
- 25.07.2024. G^3-LQ: Marrying Hyperbolic Alignment with Explicit Semantic-Geometric Modeling for 3D Visual Grounding
Presented by Lisa - 11.07.2024. ART3D: 3D Gaussian Splatting for Text-Guided Artistic Scenes Generation.
Presented by Rafael - 04.07.2024. Metric3D v2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation
Presented by Christian - 27.06.2024. A Unified Framework for Human-centric Point Cloud Video Understanding
Presented by Irene - 20.06.2024 . 3D-LLM: Injecting the 3D World into Large Language Models.
Presented by Lisa - 03.06.2024. TTT-KD: Test-Time Training for 3D Semantic Segmentation through Knowledge Distillation from Foundation Models
Presented by Lisa - 23.05.2024. Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos
Presented by Irene - 16.05.2024 . Wonder3D
Presented by Wiktor - 06.04.2024. VG4D: Vision-Language Model Goes 4D Video Recognition
Presented by Irene - 30.04.2024. Probing the 3D Awareness of Visual Foundation Models
Presented by Lisa - 24.04.2024. N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields
Presented by Lisa - 03.04.2024. 3D Gaussian Splatting
Presented by Lisa - 27.03.2024. Overview SLAM
Presented by Christian - 13.03.2024. ULIP and ULIP 2
Presented by Lisa and Wiktor - 06.03.2024. Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
Presented by Christian - 28.02.2024. Point Transformer V3: Simpler, Faster, Stronger
Presented by Irene - 20.02.2024. Segment3D: Learning Fine-Grained Class-Agnostic 3D Segmentation without Manual Labels
Presented by Lisa