Highlights
German Pattern Recognition Award 2022
Dr. Dengxin Dai has received the prestigious German Pattern Recognition Award 2022. The award is annually granted for outstanding, internationally visible research in the fields of pattern recognition, computer vision, and machine learning. It was granted to Dr. Dai this year for his outstanding scientific contributions in the area of […]
Dengxin Dai receives the Golden Owl Award
We are very proud to announce that Dr. Dengxin Dai has received the Golden Owl Award 2021 for exceptional teaching.
The Golden Owl honours excellent teachers. The Owl is awarded by VSETH, ETH Zurich’s student association.
All ETH members with a teaching assignment can be nominated for the Golden Owl. One lecturer […]
News
02/06/2023:
Dengxin Dai has joined Huawei Zurich Research Center as Director of Computer Vision
27/02/2023:
Six papers are accepted to CVPR’23.
15/01/2023:
One paper accepted to ICLR’23, two papers to ICRA’23, one paper to IJCV.
24/10/2022:
Dengxin Dai has given an invited talk at the ECCV’22 workshop on 3D Perception for Autonomous Driving
10/10/2022:
One paper is accepted by NeurIPS’22 as Oral.
10/10/2022:
We won the 1st place in Waymo Open Dataset Challenge 2022 on Motion Prediction.
10/10/2022:
Dengxin Dai is Associate Editor of ICRA 2023.
10/08/2022:
Three papers accepted to ECCV 2022.
13/05/2022:
Dengxin Dai has joined the IJCV Editorial Board.
13/05/2022:
Lukas Hoyer has been awarded the ETH Medal for his outstanding Master’s Theses done with Dengxin Dai.
Scientific Mission
The scientific mission of VAS is to develop robust and scalable perception systems for real-world applications. We focus on deep learning-based perception for autonomous systems such as autonomous driving. We are especially fascinated about scaling existing visual perception models to novel domains (e.g. adverse weather/lighting conditions, low-quality data), to more data modality (e.g. LiDAR, Radar, Events, Audio, HD Maps), to unseen classes (e.g. rare classes), and to new tasks. The relevant research topics are summarised in the diagram shown on the right.

Publications
IJCV (under review), 2022
a comprehensive study on the robustness of LiDAR semantic segmentation methods
ICRA, 2022
The first end-to-end approach to learn to optimize the LiDAR beam configuration for given applications
CVPR (Oral), 2022
A novel simulation approach to simulate snowfall effects into existing LiDAR dataset to train robust LiDAR-based perception methods for adverse weather
CVPR, 2022
A novel method for long-term test-time adaptation under continually changing environments.
CVPR, 2022
ZegFormer is the first framework that decouple the zero-shot semantic segmentation into: 1) class-agnostic segmentation and 2) segment-level zero-shot classification
CVPR (Oral), 2022
ScribbleKITTI, the first scribble-annotated dataset for LiDAR semantic segmentation and a novel learning method to reduce the performance gap that arises when using such weak annotations.
ECCV, 2022
A multi-resolution training approach for UDA, that combines the strengths of small high-resolution crops to preserve fine segmentation details and large low-resolution crops to capture long-range context dependencies with a learned scale attention.
NeurIPS, 2022
A novel Motion TRansformer (MTR) framework that models motion prediction as the joint optimization of global intention localization and local movement refinement. Won the championship of Waymo Open Dataset Challenge 2022 on Motion Prediction
This work develops an approach for scene understanding purely based on binaural sounds.
A novel UDA method, DAFormer, consisting of a Transformer encoder and a multi-level context-aware feature fusion decoder, improve SOTA by 10.8 mIoU for GTA->Cityscapes and 5.4 mIoU for Synthia->Cityscapes
This work presents a novel method for LiDAR-based 3D object detection in foggy weather by simulating foggy effects into standard LiDAR data..