Recent Trends in 3D Computer Vision & Deep Learning

Overview

The Seminar Course concerns recent advances in the field of 3D Computer Vision and Deep Learning. The Seminar will propose a list of recent scientific articles related to the main current research topics in the field, such as 3D keypoint detection and description, point cloud matching and registration, 3D object recognition and classification, SLAM, 3D reconstruction, 3D object pose estimation and tracking, depth prediction, 3D scene understanding.

Preliminary Meeting

The preliminary meeting will be held on Friday February 4th at 2 pm via Zoom.

Slides are available here.

List of Topics and Material

Authors

Title

Venue

Link

Tutor

Student

Hughes et al. Hydra: A Real-time Spatial Perception Engine for 3D Scene Graph Construction and Optimization arXiv 2022 paper Shun Cheng Felix
Talak et al. Neural Trees for Learning on Graphs NeurIPS 2021 paper Evin Alara
Sun et al. NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video CVPR 2021 paper Yan Di Alexiy
Cao et al. MonoScene: Monocular 3D Semantic Scene Completion CVPR 2022 paper Markus Daniel
Huang et al. DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors CVPR 2021 paper Shun Cheng Hanfeng
Zheng et al. Deep Implicit Templates for 3D Shape Representation CVPR 2021 paper Mahdi Asli
Lin et al. BARF: Bundle-Adjusting Neural Radiance Fields ICCV 2021 paper Stefano Eser Murat
Or-El et al. StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation CVPR 2022 paper Evin Saketh
Deng et al. Depth-supervised NeRF: Fewer Views and Faster Training for Free CVPR 2022 paper Hyun Jun Christian Tim
Xu et al. SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation ICCV 2021 paper Artem Nils
Wang et al. Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark ICCV 2021 paper Stefano Hesham
Chen et al. Geosim: Realistic video simulation via geometry-aware composition for self-driving CVPR 2021 paper Alexander Remi

 

Seminar - Recent Trends in 3D Computer Vision & Deep Learning (IN0014, IN2107, IN4826)

Lecturer (assistant)
Number0000004839
TypeSeminar
Duration2 SWS
TermSommersemester 2022
Language of instructionEnglish
Position within curriculaSee TUMonline
DatesSee TUMonline

Dates

  • 04.02.2022 14:00-14:30 Online: Videokonferenz / Zoom etc., Join Zoom Meeting https://tum-conf.zoom.us/j/61291803967?pwd=dUMvTXVMZkY5NEZoLzEvRlR2MzZuUT09 Meeting ID: 612 9180 3967 Passcode: 515697
  • 06.05.2022 14:00-16:00 03.13.010, Seminarraum, Introductory talk
  • 20.05.2022 14:00-16:00 03.13.010, Seminarraum, Topic: Scene understanding Students: Felix, Alara, Alexiy
  • 10.06.2022 14:00-16:00 01.09.014, Seminarraum, Topic: Nerf Students: Eser, Saketh, Christian
  • 01.07.2022 14:00-16:00 03.13.010, Seminarraum, Topic: 3D reconstruction Students: Daniel, Hanfeng, Asli
  • 08.07.2022 14:00-16:00 03.13.010, Seminarraum, Topic: Autonomous driving Students: Nils, Hesham, Remi
  • 29.07.2022 14:00-16:00 03.13.010, Seminarraum, (backup day)

Admission information

See TUMonline
Note: Please register in the matching system for the course registration (http://docmatching.in.tum.de). Interested students should attend the preliminary meeting.

Description

The Seminar Course concerns recent advances in the field of 3D Computer Vision and Deep Learning. The Seminar will propose a list of recent scientific articles related to the main current research topics in the field, such as 3D keypoint detection and description, point cloud matching and registration, 3D object recognition and classification, SLAM, 3D reconstruction, 3D object pose estimation and tracking, depth prediction, 3D scene understanding.

Links