Search Results for author:
Found 39 papers, 17 papers with code
DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features
We propose DistillNeRF, a self-supervised learning framework addressing the challenge of understanding 3D environments from limited 2D observations in autonomous driving.
SmartRefine: A Scenario-Adaptive Refinement Framework for Efficient Motion Prediction
Context information, such as road maps and surrounding agents' states, provides crucial geometric and semantic information for motion behavior prediction.
UncertaintyTrack: Exploiting Detection and Localization Uncertainty in Multi-Object Tracking
Multi-object tracking (MOT) methods have seen a significant boost in performance recently, due to strong interest from the research community and steadily improving object detection methods.
Feature Density Estimation for Out-of-Distribution Detection via Normalizing Flows
This is a post-hoc method which can be applied to any pretrained model, and involves training a lightweight auxiliary normalizing flow model to perform the out-of-distribution detection via density thresholding.
LMDrive: Closed-Loop End-to-End Driving with Large Language Models
On the other hand, previous autonomous driving methods tend to rely on limited-format inputs (e. g. sensor data and navigation waypoints), restricting the vehicle's ability to understand language information and interact with humans.
Multiple View Geometry Transformers for 3D Human Pose Estimation
In this work, we aim to improve the 3D reasoning ability of Transformers in multi-view 3D human pose estimation.
3D Human Pose Estimation
Multi-view 3D Human Pose Estimation
Uncertainty-aware 3D Object-Level Mapping with Deep Shape Priors
Unlike current state-of-the-art approaches, we explicitly model the uncertainty of the object shapes and poses during our optimization, resulting in a high-quality object-level mapping system.
Multi-view 3D Object Reconstruction and Uncertainty Modelling with Neural Shape Prior
We propose a method to model uncertainty as part of the representation and define an uncertainty-aware encoder which generates latent codes with uncertainty directly from individual input images.
ReasonNet: End-to-End Driving with Temporal and Global Reasoning
The large-scale deployment of autonomous vehicles is yet to come, and one of the major remaining challenges lies in urban dense traffic scenarios.
Ranked #1 on
Autonomous Driving
on CARLA Leaderboard
Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors
Inspired by this, we propose ASAP-RL, an efficient reinforcement learning algorithm for autonomous driving that simultaneously leverages motion skills and expert priors.
HyperMODEST: Self-Supervised 3D Object Detection with Confidence Score Filtering
Current LiDAR-based 3D object detectors for autonomous driving are almost entirely trained on human-annotated data collected in specific geographical domains with specific sensor setups, making it difficult to adapt to a different domain.
Gradient-based Maximally Interfered Retrieval for Domain Incremental 3D Object Detection
Accurate 3D object detection in all weather conditions remains a key challenge to enable the widespread deployment of autonomous vehicles, as most work to date has been performed on clear weather data.
Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss
However, image-to point representation learning for autonomous driving datasets faces two main challenges: 1) the abundance of self-similarity, which results in the contrastive losses pushing away semantically similar point and image regions and thus disturbing the local semantic structure of the learned representations, and 2) severe class imbalance as pretraining gets dominated by over-represented classes.
Estimating Regression Predictive Distributions with Sample Networks
A common approach to model uncertainty is to choose a parametric distribution and fit the data to it using maximum likelihood estimation.
InterTrack: Interaction Transformer for 3D Multi-Object Tracking
We then perform a learned regression on each track/detection feature pair to estimate affinities, and use a robust two-stage data association and track management approach to produce the final tracks.
Point Density-Aware Voxels for LiDAR 3D Object Detection
LiDAR has become one of the primary 3D object detection sensors in autonomous driving.
Dense Voxel Fusion for 3D Object Detection
Sequential fusion methods suffer from a limited number of pixel and point correspondences due to point cloud sparsity, or their performance is strictly capped by the detections of one of the modalities.
Next-Best-View Prediction for Active Stereo Cameras and Highly Reflective Objects
Depth acquisition with the active stereo camera is a challenging task for highly reflective objects.
Pattern-Aware Data Augmentation for LiDAR 3D Object Detection
Autonomous driving datasets are often skewed and in particular, lack training data for objects at farther distances from the ego vehicle.
Temporal Convolutions for Multi-Step Quadrotor Motion Prediction
Model-based control methods for robotic systems such as quadrotors, autonomous driving vehicles and flexible manipulators require motion models that generate accurate predictions of complex nonlinear system dynamics over long periods of time.
Categorical Depth Distribution Network for Monocular 3D Object Detection
We validate our approach on the KITTI 3D object detection benchmark, where we rank 1st among published monocular methods.
Learned Camera Gain and Exposure Control for Improved Visual Feature Detection and Matching
Successful visual navigation depends upon capturing images that contain sufficient useful information.
Estimating and Evaluating Regression Predictive Uncertainty in Deep Object Detectors
We show that in the context of object detection, training variance networks with negative log likelihood (NLL) can lead to high entropy predictive distributions regardless of the correctness of the output mean.
Predictive Uncertainty in Deep Object Detectors: Estimation and Evaluation
We show that in the context of object detection, training variance networks with negative log likelihood (NLL) can lead to high entropy predictive distributions regardless of the correctness of the output mean.
Confidence Guided Stereo 3D Object Detection with Split Depth Estimation
To tackle these two issues, we propose CG-Stereo, a confidence-guided stereo 3D object detection pipeline that uses separate decoders for foreground and background pixels during depth estimation, and leverages the confidence estimation from the depth estimation network as a soft attention mechanism in the 3D object detector.
3D Object Detection From Stereo Images
Autonomous Driving
+3
Visual Measurement Integrity Monitoring for UAV Localization
In this paper, we propose a novel approach inspired by RAIM to monitor the integrity of optimization-based visual localization and calculate the protection level of a state estimate, i. e. the largest possible translational error in each direction.
Object-Centric Stereo Matching for 3D Object Detection
The issue with existing stereo matching networks is that they are designed for disparity estimation, not 3D object detection; the shape and accuracy of object point clouds are not the focus.
3D Object Detection From Stereo Images
Autonomous Driving
+5
Improving 3D Object Detection for Pedestrians with Virtual Multi-View Synthesis Orientation Estimation
Accurately estimating the orientation of pedestrians is an important and challenging task for autonomous driving because this information is essential for tracking and predicting pedestrian behavior.
Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction
We present MonoPSR, a monocular 3D object detection method that leverages proposals and shape reconstruction.
Ranked #13 on
Vehicle Pose Estimation
on KITTI Cars Hard
BayesOD: A Bayesian Approach for Uncertainty Estimation in Deep Object Detectors
When incorporating deep neural networks into robotic systems, a major challenge is the lack of uncertainty measures associated with their output predictions.
Network Uncertainty Informed Semantic Feature Selection for Visual SLAM
In order to facilitate long-term localization using a visual simultaneous localization and mapping (SLAM) algorithm, careful feature selection can help ensure that reference points persist over long durations and the runtime and storage complexity of the algorithm remain consistent.
Aerial Imagery for Roof Segmentation: A Large-Scale Dataset towards Automatic Mapping of Buildings
In this paper, we present a new large-scale benchmark dataset termed Aerial Imagery for Roof Segmentation (AIRS).
Encoderless Gimbal Calibration of Dynamic Multi-Camera Clusters
In this paper, we present an encoderless approach for DCC calibration which simultaneously estimates the kinematic parameters of the transformation chain as well as the unknown joint angles.
Leveraging Pre-Trained 3D Object Detection Models For Fast Ground Truth Generation
Training 3D object detectors for autonomous driving has been limited to small datasets due to the effort required to generate annotations.
A Hierarchical Deep Architecture and Mini-Batch Selection Method For Joint Traffic Sign and Light Detection
The root cause of this issue is that no public dataset contains both traffic light and sign labels, which leads to difficulties in developing a joint detection framework.
Multi-Step Prediction of Dynamic Systems with Recurrent Neural Networks
In this work, the state initialization problem is addressed using Neural Networks (NNs) to effectively train a variety of RNNs for modeling two aerial vehicles, a helicopter and a quadrotor, from experimental data.
In Defense of Classical Image Processing: Fast Depth Completion on the CPU
With the rise of data driven deep neural networks as a realization of universal function approximators, most research on computer vision problems has moved away from hand crafted classical image processing algorithms.
3D Scan Registration using Curvelet Features in Planetary Environments
Topographic mapping in planetary environments relies on accurate 3D scan registration methods.
Degenerate Motions in Multicamera Cluster SLAM with Non-overlapping Fields of View
An analysis of the relative motion and point feature model configurations leading to solution degeneracy is presented, for the case of a Simultaneous Localization and Mapping system using multicamera clusters with non-overlapping fields-of-view.
