Yancong Lin (林彦聪)

Guest researcher, Institute of Geodesy and Photogrammetry, ETH Zurich.

Postdoc, Intelligent Vehicles Group, Cognitive Robotics, TUDelft.

Working with Prof. Konrad Schindler and Dr. Holger Caesar.

PhD from Pattern Recognition & Bioinformatics, TUDelft (2022).

Advisors: Dr. Jan van Gemert and Dr. Silvia-Laura Pintea.


Research on built-in knowledge priors for scalable perception models.
Collaboration with AIIR on automated inspection for aircraft engines.

I am actively seeking a research scientist role in the industry or an assistant professor position in academia.


Email  /  Google Scholar  /  Github  /  LinkedIn  / 

profile
About me

I am interested in creating data-efficient AI models for various computer vision/robotics perception tasks by pre-wiring deep learning with generic innate knowledge priors. This eliminates the need to collect and annotate large datasets, as built-in knowledge no longer has to be learned. My work exhibits leading performance while reducing data demand substantially, particularly in processing images and point clouds.

News

01/10/2024     Moved to ETH Zurich as an academic guest at the Institute of Geodesy and Photogrammetry.

17/07/2024     Master thesis: Arbër, SfM applications for 3D reconstruction from 2D avionics industrial inspection videos.

11/07/2024     Master thesis: Tibbe, MultiViT: 2D to 3D transfer learning using a jointly optimized Vision Transformer.

17/06/2024     ICP-Flow has won the Argoverse 2 Scene Flow Challenge (unsupervised track).

28/02/2024     Our submission to CVPR'24 on LiDAR scene flow estimation has been accepted.

29/01/2024     Our submission to ICRA'24 on active learning for LiDAR semantic segmentation has been accepted.

18/12/2023     Research grant:NWO NGF AiNed XS Europa (80k euros), in collaboration with Prof. Konrad Schindler, ETH.

13/07/2023     Our submission to ICCV'23 on why classification helps regression has been accepted.

26/06/2023     Nafie successfully defended his master thesis: BladeNeRF. Cum laude!

19/10/2022     I am an outstanding reviewer, ECCV'22.

01/10/2022     Postdoc at the Intelligent Vehicles Group, 3mE, TUDelft.

30/09/2022     Our submission to BMVC'22 on mirror symmetries has been accepted.

21/05/2022     I am an outstanding reviewer, CVPR'22.

25/04/2022     I have successfully defended my phd dissertation.

03/03/2022     Our submission to CVPR'22 on vanishing points has been accepted.

01/01/2022     New project with an industrial partner: computer vision for aircraft engine inspection.

18/08/2021     Our submission to ICCV'21 workshop (Deep Learning for Geometric Computing): Best student paper award.

23/07/2021     ICCV'21 workshop: 2nd Visual Inductive Priors for Data-Efficient Deep Learning Workshop,

12/07/2021     Congrats to Andrea on defending his master thesis.

26/05/2021     Our submission to ICIP'21 has been accepted.

01/10/2020     Congrats to Kang Lang on defending his master thesis.

23/08/2020     ECCV'20 workshop: 1st Visual Inductive Priors for Data-Efficient Deep Learning Workshop,

04/07/2020     Our submission to ECCV'20 on wireframe parsing has been accepted.

Publications
Bosch Street Dataset: A Multi-Modal Dataset with Imaging Radar for Automated Driving ..., Yancong Lin , ...
ArXiv, 2024
arXiv

BSD offers a unique integration of high-resolution imaging radar, lidar, and camera sensors.

ICP-Flow: LiDAR Scene Flow Estimation with ICP
Yancong Lin , Holger Caesar
CVPR, 2024
arXiv / Code

Clustering + ICP, w/o learning, w/o training data: a strong baseline for LiDAR scene flow.

Winner, (Unsupervised) Argoverse 2 Scene Flow Challenge, CVPR 2024.

BaSAL: Size Balanced Warm Start Active Learning for LiDAR Semantic Segmentation
Jiarong Wei, Yancong Lin *, Holger Caesar
ICRA, 2024
arXiv / Code

Class imbalance and cold start in active learning: size-based partition to rescue

A step towards understanding why classification helps regression
Silvia-Laura Pintea, Yancong Lin, Jouke Dijkstra, Silvia-Laura Pintea, Jan van Gemert
ICCV, 2023
arXiv / Code

For a regression task, if the data sampling is imbalanced, then add a classification loss.

Deep Vanishing Point Detection: Geometric priors make dataset variations vanish
Yancong Lin, Ruben Wiserma, Silvia-Laura Pintea, Klaus Hildebrandt, Elmar Eisemann, Jan van Gemert
CVPR, 2022
arXiv / Code

Hough Transform and Gaussian sphere priors for data-efficient and domain-robust vanishing point detection.

NeRD++: Improved 3D-mirror symmetry learning from a single image
Yancong Lin, Silvia-Laura Pintea, Jan van Gemert
BMVC, 2022
arXiv / Code

Detecting 3D mirror plane from a single image, using feature correlations, mirroring, multi-scale spherical convs.

Investigating transformers in the decomposition of polygonal shapes as point collections
Andrea Alfieri, Yancong Lin, Jan van Gemert
ICCV Workshop (Best student paper!), 2021
arXiv

Exploit auto-regressive and parallel transformers in predicting collections of points (polygons).

Semi-Supervised Lane Detection with Deep Hough Transform
Yancong Lin, Silvia-Laura Pintea, Jan van Gemert
ICIP, 2021
Code / arXiv

Exploit lane representations in the Hough space from unlabel data.

Deep Hough Transform Line Priors
Yancong Lin, Silvia-Laura Pintea, Jan van Gemert
ECCV, 2020
Code / arXiv

Reduce data dependency by adding line priors through a trainable Hough transform module.

Quality Index for Stereoscopic Images by Jointly Evaluating Cyclopean Amplitude and Cyclopean Phase
Yancong Lin, Jiachen Yang, Wen Lu, Qinggang Meng, Zhihan Lv, Houbing Song
IEEE Journal of Selected Topics in Signal Processing, 2016

Stereo image quality assessment using binocular vision models and low-level features.

Core contribution of master thesis.

Service

Reviewer: CVPR/ICCV/ECCV, IEEE Transactions on Image Processing.

Teaching Assistant: CS4245 Computer Vision by Deep Learning, 2019/2020 Q4.

Teaching Assistant: IN4393 Computer Vision, 2018/19 Q3.

Miscellaneous

Fitness (powerlifting) / Auto and Autobahn enthusiast / Formula 1 / Premier League /


Template from Jon Barron.