1.4k citations · 3.1k across the 72 of their papers we have counts for
92 papers
Test-time Training for Hyperspectral Image Super-resolution
Ke Li, Luc Van Gool, Dengxin Dai
The progress on Hyperspectral image (HSI) super-resolution (SR) is still lagging behind the research of RGB image SR. HSIs usually have a high number of spectral bands, so accurate…
MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation
Linyan Yang, Lukas Hoyer, Mark Weber +6
Unsupervised Domain Adaptation (UDA) is the task of bridging the domain gap between a labeled source domain, e.g., synthetic data, and an unlabeled target domain. We observe that c…
2D Feature Distillation for Weakly- and Semi-Supervised 3D Semantic Segmentation
Ozan Unal, Dengxin Dai, Lukas Hoyer +2
As 3D perception problems grow in popularity and the need for large-scale labeled datasets for LiDAR semantic segmentation increase, new methods arise that aim to reduce the necess…
Discwise Active Learning for LiDAR Semantic Segmentation
Ozan Unal, Dengxin Dai, Ali Tamer Unal +1
While LiDAR data acquisition is easy, labeling for semantic segmentation remains highly time consuming and must therefore be done selectively. Active learning (AL) provides a solut…
LiDAR Meta Depth Completion
Wolfgang Boettcher, Lukas Hoyer, Ozan Unal +2
Depth estimation is one of the essential tasks to be addressed when creating mobile autonomous systems. While monocular depth estimation methods have improved in recent times, dept…
MTR++: Multi-Agent Motion Prediction with Symmetric Scene Modeling and Guided Intention Querying
Shaoshuai Shi, Li Jiang, Dengxin Dai +1
Motion prediction is crucial for autonomous driving systems to understand complex driving scenarios and make informed decisions. However, this task is challenging due to the divers…
HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation
Jian Ding, Nan Xue, Gui-Song Xia +2
Current semantic segmentation models have achieved great success under the independent and identically distributed (i.i.d.) condition. However, in real-world applications, test dat…
Self-supervised Pre-training with Masked Shape Prediction for 3D Scene Understanding
Li Jiang, Zetong Yang, Shaoshuai Shi +3
Masked signal modeling has greatly advanced self-supervised pre-training for language and 2D images. However, it is still not fully explored in 3D scene understanding. Thus, this p…
FreePoint: Unsupervised Point Cloud Instance Segmentation
Zhikai Zhang, Jian Ding, Li Jiang +2
Instance segmentation of point clouds is a crucial task in 3D field with numerous applications that involve localizing and segmenting objects in a scene. However, achieving satisfa…
Federated Incremental Semantic Segmentation
Jiahua Dong, Duzhen Zhang, Yang Cong +3
Federated learning-based semantic segmentation (FSS) has drawn widespread attention via decentralized training on local clients. However, most FSS models assume categories are fixe…
EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation
Suman Saha, Lukas Hoyer, Anton Obukhov +2
With autonomous industries on the rise, domain adaptation of the visual perception stack is an important research direction due to the cost savings promise. Much prior art was dedi…
Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation
Lukas Hoyer, Dengxin Dai, Luc Van Gool
Unsupervised domain adaptation (UDA) and domain generalization (DG) enable machine learning models trained on a source domain to perform well on unlabeled or even unseen target dom…
TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction
Zhejun Zhang, Alexander Liniger, Dengxin Dai +2
Data-driven simulation has become a favorable way to train and test autonomous driving algorithms. The idea of replacing the actual environment with a learned simulator has also be…
No One Left Behind: Real-World Federated Class-Incremental Learning
Jiahua Dong, Hongliu Li, Yang Cong +3
Federated learning (FL) is a hot collaborative training framework via aggregating model parameters of decentralized local clients. However, most FL methods unreasonably assume data…
Benchmarking the Robustness of LiDAR Semantic Segmentation Models
Xu Yan, Chaoda Zheng, Ying Xue +3
When using LiDAR semantic segmentation models for safety-critical applications such as autonomous driving, it is essential to understand and improve their robustness with respect t…
Simulating Road Spray Effects in Automotive Lidar Sensor Models
Clemens Linnhoff, Dominik Scheuble, Mario Bijelic +5
Modeling perception sensors is key for simulation based testing of automated driving functions. Beyond weather conditions themselves, sensors are also subjected to object dependent…
One-Shot Domain Adaptive and Generalizable Semantic Segmentation with Class-Aware Cross-Domain Transformers
Rui Gong, Qin Wang, Dengxin Dai +1
Unsupervised sim-to-real domain adaptation (UDA) for semantic segmentation aims to improve the real-world test performance of a model trained on simulated data. It can save the cos…
MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
Lukas Hoyer, Dengxin Dai, Haoran Wang +1
In unsupervised domain adaptation (UDA), a model trained on source data (e.g. synthetic) is adapted to target data (e.g. real-world) without access to target annotation. Most previ…
Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts
Qi Fan, Mattia Segu, Yu-Wing Tai +4
Improving model's generalizability against domain shifts is crucial, especially for safety-critical applications such as autonomous driving. Real-world domain styles can vary subst…
MTR-A: 1st Place Solution for 2022 Waymo Open Dataset Challenge -- Motion Prediction
Shaoshuai Shi, Li Jiang, Dengxin Dai +1
In this report, we present the 1st place solution for motion prediction track in 2022 Waymo Open Dataset Challenges. We propose a novel Motion Transformer framework for multimodal…
Motion Transformer with Global Intention Localization and Local Movement Refinement
Shaoshuai Shi, Li Jiang, Dengxin Dai +1
Predicting multimodal future behavior of traffic participants is essential for robotic vehicles to make safe decisions. Existing works explore to directly predict future trajectori…
Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes
Yu-Huan Wu, Da Zhang, Le Zhang +4
Current efficient LiDAR-based detection frameworks are lacking in exploiting object relations, which naturally present in both spatial and temporal manners. To this end, we introdu…
HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection
Tim Broedermann, Christos Sakaridis, Dengxin Dai +1
Besides standard cameras, autonomous vehicles typically include multiple additional sensors, such as lidars and radars, which help acquire richer information for perceiving the con…
Bi-level Alignment for Cross-Domain Crowd Counting
Shenjian Gong, Shanshan Zhang, Jian Yang +2
Recently, crowd density estimation has received increasing attention. The main challenge for this task is to achieve high-quality manual annotations on a large amount of training d…