Search Results for author:
Found 21 papers, 14 papers with code
NeuroNCAP: Photorealistic Closed-loop Safety Testing for Autonomous Driving
We present a versatile NeRF-based simulator for testing autonomous driving (AD) software systems, designed with a focus on sensor-realistic closed-loop evaluation and the creation of safety-critical scenarios.
Label-Efficient 3D Object Detection For Road-Side Units
We address this challenge by devising a label-efficient object detection method for RSU based on unsupervised object discovery.
DPFT: Dual Perspective Fusion Transformer for Camera-Radar-based Object Detection
However, cameras are not robust against severe weather conditions, lidar sensors are expensive, and the performance of radar-based perception is still inferior to the others.
Towards learning-based planning:The nuPlan benchmark for real-world autonomous driving
Beyond the dataset, we provide a simulation and evaluation framework that enables a planner's actions to be simulated in closed-loop to account for interactions with other traffic participants.
ICP-Flow: LiDAR Scene Flow Estimation with ICP
We incorporate this rigid-motion assumption into our design, where the goal is to associate objects over scans and then estimate the locally rigid transformations.
VLPrompt: Vision-Language Prompting for Panoptic Scene Graph Generation
Panoptic Scene Graph Generation (PSG) aims at achieving a comprehensive image understanding by simultaneously segmenting objects and predicting relations among objects.
Ranked #1 on
Panoptic Scene Graph Generation
on PSG Dataset
Graph Convolutional Networks for Complex Traffic Scenario Classification
Most methods on scenario classification do not work for complex scenarios with diverse environments (highways, urban) and interaction with other traffic agents.
BaSAL: Size-Balanced Warm Start Active Learning for LiDAR Semantic Segmentation
By sampling object clusters according to their size, we can thus create a size-balanced dataset that is also more class-balanced.
Offline Tracking with Object Permanence
In this work, we propose an offline tracking model that focuses on occluded object tracks.
Ranked #31 on
3D Multi-Object Tracking
on nuScenes
UniBEV: Multi-modal 3D Object Detection with Uniform BEV Encoders for Robustness against Missing Sensor Modalities
To validate its effectiveness, we compare UniBEV to state-of-the-art BEVFusion and MetaBEV on nuScenes over all sensor input combinations.
HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation
Existing unbiased methods tackle the long-tail problem by data/loss rebalancing to favor low-frequency relations.
Ranked #2 on
Panoptic Scene Graph Generation
on PSG Dataset
SliceMatch: Geometry-guided Aggregation for Cross-View Pose Estimation
We propose SliceMatch, which consists of ground and aerial feature extractors, feature aggregators, and a pose predictor.
Panoptic nuScenes: A Large-Scale Benchmark for LiDAR Panoptic Segmentation and Tracking
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
NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles
In this work, we propose the world's first closed-loop ML-based planning benchmark for autonomous driving.
The efficacy of Neural Planning Metrics: A meta-analysis of PKL on nuScenes
A high-performing object detection system plays a crucial role in autonomous driving (AD).
nuScenes: A multimodal dataset for autonomous driving
Most autonomous vehicles, however, carry a combination of cameras and range sensors such as lidar and radar.
Ranked #312 on
3D Object Detection
on nuScenes
(using extra training data)
PointPillars: Fast Encoders for Object Detection from Point Clouds
These benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds.
Weakly Supervised Object Localization Using Things and Stuff Transfer
We propose to help weakly supervised object localization for classes where location annotations are not available, by transferring things and stuff knowledge from a source set with available annotations.
COCO-Stuff: Thing and Stuff Classes in Context
To understand stuff and things in context we introduce COCO-Stuff, which augments all 164K images of the COCO 2017 dataset with pixel-wise annotations for 91 stuff classes.
Ranked #1 on
Semantic Segmentation
on COCO-Stuff
Region-based semantic segmentation with end-to-end training
We propose a novel method for semantic segmentation, the task of labeling each pixel in an image with a semantic class.
Ranked #1 on
Semantic Segmentation
on SIFT-flow
Joint Calibration for Semantic Segmentation
Semantic segmentation is the task of assigning a class-label to each pixel in an image.
Ranked #2 on
Semantic Segmentation
on SIFT-flow
