Optical flow estimation is very challenging in situations with transparent or occluded objects.
Deep learning has led to remarkable strides in scene understanding with panoptic segmentation emerging as a key holistic scene interpretation task.
To address these limitations, we introduce AmodalSynthDrive, a synthetic multi-task multi-modal amodal perception dataset.
Safety and efficiency are paramount in healthcare facilities where the lives of patients are at stake.
Amodal panoptic segmentation aims to connect the perception of the world to its cognitive understanding.
To enable robots to reason with this capability, we formulate and propose a novel task that we name amodal panoptic segmentation.
Ranked #1 on Amodal Panoptic Segmentation on BDD100K val
In this technical report, we describe our EfficientLPT architecture that won the panoptic tracking challenge in the 7th AI Driving Olympics at NeurIPS 2021.
Panoptic scene understanding and tracking of dynamic agents are essential for robots and automated vehicles to navigate in urban environments.
Ranked #1 on Panoptic Segmentation on Panoptic nuScenes test
Panoptic segmentation of point clouds is a crucial task that enables autonomous vehicles to comprehend their vicinity using their highly accurate and reliable LiDAR sensors.
In this technical report, we present key details of our winning panoptic segmentation architecture EffPS_b1bs4_RVC.
In this paper, we introduce a novel perception task denoted as multi-object panoptic tracking (MOPT), which unifies the conventionally disjoint tasks of semantic segmentation, instance segmentation, and multi-object tracking.
Understanding the scene in which an autonomous robot operates is critical for its competent functioning.
Ranked #1 on Panoptic Segmentation on KITTI Panoptic Segmentation
This problem is extremely challenging as pre-existing maps cannot be leveraged for navigation due to structural changes that may have occurred.
Indoor localization is one of the crucial enablers for deployment of service robots.
To address this limitation, we propose a mutimodal semantic segmentation framework that dynamically adapts the fusion of modality-specific features while being sensitive to the object category, spatial location and scene context in a self-supervised manner.
Ranked #1 on Semantic Segmentation on Freiburg Forest