Uni-to-Multi Modal Knowledge Distillation for Bidirectional LiDAR-Camera Semantic Segmentation
Combining LiDAR points and images for robust semantic segmentation has shown great
potential. However, the heterogeneity between the two modalities (eg the density, the field of …
potential. However, the heterogeneity between the two modalities (eg the density, the field of …
LPFormer: LiDAR pose estimation transformer with multi-task network
Due to the difficulty of acquiring large-scale 3D human keypoint annotation, previous
methods for 3D human pose estimation (HPE) have often relied on 2D image features and …
methods for 3D human pose estimation (HPE) have often relied on 2D image features and …
Panoptic Perception for Autonomous Driving: A Survey
Y Li, L Xu - arxiv preprint arxiv:2408.15388, 2024 - arxiv.org
Panoptic perception represents a forefront advancement in autonomous driving technology,
unifying multiple perception tasks into a singular, cohesive framework to facilitate a thorough …
unifying multiple perception tasks into a singular, cohesive framework to facilitate a thorough …
Small, versatile and mighty: A range-view perception framework
Q Meng, X Wang, JB Wang, L Yan, K Wang - arxiv preprint arxiv …, 2024 - arxiv.org
Despite its compactness and information integrity, the range view representation of LiDAR
data rarely occurs as the first choice for 3D perception tasks. In this work, we further push the …
data rarely occurs as the first choice for 3D perception tasks. In this work, we further push the …
Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion
An important paradigm in 3D object detection is the use of multiple modalities to enhance
accuracy in both normal and challenging conditions, particularly for long-tail scenarios. To …
accuracy in both normal and challenging conditions, particularly for long-tail scenarios. To …
A Point-Based Approach to Efficient LiDAR Multi-Task Perception
Multi-task networks can potentially improve performance and computational efficiency
compared to single-task networks, facilitating online deployment. However, current multi …
compared to single-task networks, facilitating online deployment. However, current multi …
3D-JEPA: A Joint Embedding Predictive Architecture for 3D Self-Supervised Representation Learning
Invariance-based and generative methods have shown a conspicuous performance for 3D
self-supervised representation learning (SSRL). However, the former relies on hand-crafted …
self-supervised representation learning (SSRL). However, the former relies on hand-crafted …
LiSD: An Efficient Multi-Task Learning Framework for LiDAR Segmentation and Detection
With the rapid proliferation of autonomous driving, there has been a heightened focus on the
research of lidar-based 3D semantic segmentation and object detection methodologies …
research of lidar-based 3D semantic segmentation and object detection methodologies …