2022
IJCV (under review), 2022
a comprehensive study on the robustness of LiDAR semantic segmentation methods
CVPR, 2022
a novel pipeline to generate Neural Radiance Fields (NeRF) of an object or a scene of a specific class, conditioned on a single input image
CVPR, 2022
a novel co-learning framework (CoSSL) with decoupled representation learning and classifier learning for imbalanced SSL
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
2021
We present Scale-aware Domain Adaptive Faster R-CNN, a model aiming at improving the cross-domain robustness of object detection.
We propose a projection-based method for semantic segmentation of LiDar data, called Multi-scale Interaction Network (MINet), which is very efficient and accurate.
We present a domain flow generation (DLOW) model to bridge two different domains by generating a continuous sequence of intermediate domains flowing from one domain to the other.
We introduce Task Switching Networks (TSNs), a task-conditioned architecture with a single unified encoder/decoder for efficient multi-task learning.
Preprint
We propose a novel co-learning framework (CoSSL) with decoupled representation learning and classifier learning for imbalanced SSL.
Preprint
Zero-shot semantic segmentation (ZS3) aims to segment the novel categories that have not been seen in the training. We propose to decouple the ZS3 into two sub-tasks: 1) a class-agnostic grouping task to group the pixels into segments. 2) a zero-shot classification task on segments.
This work presents a novel method for LiDAR-based 3D object detection in foggy weather by simulating foggy effects into standard LiDAR data..
ACDC is a large-scale dataset for training and testing semantic segmentation methods for four adverse visual conditions: fog, nighttime, rain, and snow.
A novel method to leverage the guidance from self-supervised depth estimation to bridge the domain gap for semantic segmentation, achieving state-of-the-art performance..
A novel manner to learn end-to-end driving from a reinforcement learning expert that maps bird's-eye view images to continuous low-level actions, achieving the state-of-the-art perfomrance.