Search Results for author: Dragomir Anguelov

Found 65 papers, 19 papers with code

PVTransformer: Point-to-Voxel Transformer for Scalable 3D Object Detection

no code implementations5 May 2024 Zhaoqi Leng, Pei Sun, Tong He, Dragomir Anguelov, Mingxing Tan

3D object detectors for point clouds often rely on a pooling-based PointNet to encode sparse points into grid-like voxels or pillars.

3D Object Detection Object +1

MoST: Multi-modality Scene Tokenization for Motion Prediction

no code implementations CVPR 2024 Norman Mu, Jingwei Ji, Zhenpei Yang, Nate Harada, Haotian Tang, Kan Chen, Charles R. Qi, Runzhou Ge, Kratarth Goel, Zoey Yang, Scott Ettinger, Rami Al-Rfou, Dragomir Anguelov, Yin Zhou

This symbolic representation is a high-level abstraction of the real world, which may render the motion prediction model vulnerable to perception errors (e. g., failures in detecting open-vocabulary obstacles) while missing salient information from the scene context (e. g., poor road conditions).

General Knowledge motion prediction

LEF: Late-to-Early Temporal Fusion for LiDAR 3D Object Detection

no code implementations28 Sep 2023 Tong He, Pei Sun, Zhaoqi Leng, Chenxi Liu, Dragomir Anguelov, Mingxing Tan

We propose a late-to-early recurrent feature fusion scheme for 3D object detection using temporal LiDAR point clouds.

3D Object Detection Object +1

Unsupervised 3D Perception with 2D Vision-Language Distillation for Autonomous Driving

no code implementations ICCV 2023 Mahyar Najibi, Jingwei Ji, Yin Zhou, Charles R. Qi, Xinchen Yan, Scott Ettinger, Dragomir Anguelov

Closed-set 3D perception models trained on only a pre-defined set of object categories can be inadequate for safety critical applications such as autonomous driving where new object types can be encountered after deployment.

Autonomous Driving Knowledge Distillation

3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels

no code implementations CVPR 2023 Zhenzhen Weng, Alexander S. Gorban, Jingwei Ji, Mahyar Najibi, Yin Zhou, Dragomir Anguelov

We show that by training on a large training set from Waymo Open Dataset without any human annotated keypoints, we are able to achieve reasonable performance as compared to the fully supervised approach.

MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences

1 code implementation CVPR 2023 Yingwei Li, Charles R. Qi, Yin Zhou, Chenxi Liu, Dragomir Anguelov

The MoDAR modality propagates object information from temporal contexts to a target frame, represented as a set of virtual points, one for each object from a waypoint on a forecasted trajectory.

3D Object Detection Motion Forecasting +2

WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting

no code implementations7 Apr 2023 Kan Chen, Runzhou Ge, Hang Qiu, Rami Ai-Rfou, Charles R. Qi, Xuanyu Zhou, Zoey Yang, Scott Ettinger, Pei Sun, Zhaoqi Leng, Mustafa Baniodeh, Ivan Bogun, Weiyue Wang, Mingxing Tan, Dragomir Anguelov

To study the effect of these modular approaches, design new paradigms that mitigate these limitations, and accelerate the development of end-to-end motion forecasting models, we augment the Waymo Open Motion Dataset (WOMD) with large-scale, high-quality, diverse LiDAR data for the motion forecasting task.

Motion Forecasting

GINA-3D: Learning to Generate Implicit Neural Assets in the Wild

no code implementations CVPR 2023 Bokui Shen, Xinchen Yan, Charles R. Qi, Mahyar Najibi, Boyang Deng, Leonidas Guibas, Yin Zhou, Dragomir Anguelov

Modeling the 3D world from sensor data for simulation is a scalable way of developing testing and validation environments for robotic learning problems such as autonomous driving.

Autonomous Driving Representation Learning

Imitation Is Not Enough: Robustifying Imitation with Reinforcement Learning for Challenging Driving Scenarios

no code implementations21 Dec 2022 Yiren Lu, Justin Fu, George Tucker, Xinlei Pan, Eli Bronstein, Rebecca Roelofs, Benjamin Sapp, Brandyn White, Aleksandra Faust, Shimon Whiteson, Dragomir Anguelov, Sergey Levine

To our knowledge, this is the first application of a combined imitation and reinforcement learning approach in autonomous driving that utilizes large amounts of real-world human driving data.

Autonomous Driving Imitation Learning +2

JFP: Joint Future Prediction with Interactive Multi-Agent Modeling for Autonomous Driving

no code implementations16 Dec 2022 Wenjie Luo, Cheolho Park, Andre Cornman, Benjamin Sapp, Dragomir Anguelov

We propose JFP, a Joint Future Prediction model that can learn to generate accurate and consistent multi-agent future trajectories.

Autonomous Driving Decoder +1

NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors

1 code implementation CVPR 2023 Congyue Deng, Chiyu "Max'' Jiang, Charles R. Qi, Xinchen Yan, Yin Zhou, Leonidas Guibas, Dragomir Anguelov

Formulating single-view reconstruction as an image-conditioned 3D generation problem, we optimize the NeRF representations by minimizing a diffusion loss on its arbitrary view renderings with a pretrained image diffusion model under the input-view constraint.

3D Generation 3D Reconstruction

PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds

no code implementations24 Oct 2022 Zhaoqi Leng, Shuyang Cheng, Benjamin Caine, Weiyue Wang, Xiao Zhang, Jonathon Shlens, Mingxing Tan, Dragomir Anguelov

To alleviate the cost of hyperparameter tuning and iterative pseudo labeling, we develop a population-based data augmentation framework for 3D detection, named AutoPseudoAugment.

Data Augmentation Pseudo Label

CramNet: Camera-Radar Fusion with Ray-Constrained Cross-Attention for Robust 3D Object Detection

no code implementations17 Oct 2022 Jyh-Jing Hwang, Henrik Kretzschmar, Joshua Manela, Sean Rafferty, Nicholas Armstrong-Crews, Tiffany Chen, Dragomir Anguelov

Fusing camera and radar data is challenging, however, as each of the sensors lacks information along a perpendicular axis, that is, depth is unknown to camera and elevation is unknown to radar.

Autonomous Driving Monocular 3D Object Detection +3

Improving the Intra-class Long-tail in 3D Detection via Rare Example Mining

no code implementations15 Oct 2022 Chiyu Max Jiang, Mahyar Najibi, Charles R. Qi, Yin Zhou, Dragomir Anguelov

Continued improvements in deep learning architectures have steadily advanced the overall performance of 3D object detectors to levels on par with humans for certain tasks and datasets, where the overall performance is mostly driven by common examples.

3D Object Detection Active Learning +3

LESS: Label-Efficient Semantic Segmentation for LiDAR Point Clouds

no code implementations14 Oct 2022 Minghua Liu, Yin Zhou, Charles R. Qi, Boqing Gong, Hao Su, Dragomir Anguelov

Our method co-designs an efficient labeling process with semi/weakly supervised learning and is applicable to nearly any 3D semantic segmentation backbones.

3D Semantic Segmentation Autonomous Driving +3

Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving

no code implementations14 Oct 2022 Mahyar Najibi, Jingwei Ji, Yin Zhou, Charles R. Qi, Xinchen Yan, Scott Ettinger, Dragomir Anguelov

Learning-based perception and prediction modules in modern autonomous driving systems typically rely on expensive human annotation and are designed to perceive only a handful of predefined object categories.

Autonomous Driving Trajectory Prediction

LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds

no code implementations10 Oct 2022 Chenxi Liu, Zhaoqi Leng, Pei Sun, Shuyang Cheng, Charles R. Qi, Yin Zhou, Mingxing Tan, Dragomir Anguelov

Developing neural models that accurately understand objects in 3D point clouds is essential for the success of robotics and autonomous driving.

3D Object Detection Autonomous Driving +2

LET-3D-AP: Longitudinal Error Tolerant 3D Average Precision for Camera-Only 3D Detection

1 code implementation15 Jun 2022 Wei-Chih Hung, Vincent Casser, Henrik Kretzschmar, Jyh-Jing Hwang, Dragomir Anguelov

However, camera-only detectors have limited depth accuracy, which may cause otherwise reasonable predictions that suffer from such longitudinal localization errors to be treated as false positives.

Depth Estimation Object Detection

Waymo Open Dataset: Panoramic Video Panoptic Segmentation

1 code implementation15 Jun 2022 Jieru Mei, Alex Zihao Zhu, Xinchen Yan, Hang Yan, Siyuan Qiao, Yukun Zhu, Liang-Chieh Chen, Henrik Kretzschmar, Dragomir Anguelov

We therefore present the Waymo Open Dataset: Panoramic Video Panoptic Segmentation Dataset, a large-scale dataset that offers high-quality panoptic segmentation labels for autonomous driving.

Autonomous Driving Image Segmentation +4

StopNet: Scalable Trajectory and Occupancy Prediction for Urban Autonomous Driving

no code implementations2 Jun 2022 Jinkyu Kim, Reza Mahjourian, Scott Ettinger, Mayank Bansal, Brandyn White, Ben Sapp, Dragomir Anguelov

A whole-scene sparse input representation allows StopNet to scale to predicting trajectories for hundreds of road agents with reliable latency.

Motion Forecasting

Multi-Class 3D Object Detection with Single-Class Supervision

no code implementations11 May 2022 Mao Ye, Chenxi Liu, Maoqing Yao, Weiyue Wang, Zhaoqi Leng, Charles R. Qi, Dragomir Anguelov

While multi-class 3D detectors are needed in many robotics applications, training them with fully labeled datasets can be expensive in labeling cost.

3D Object Detection Object +1

Occupancy Flow Fields for Motion Forecasting in Autonomous Driving

no code implementations8 Mar 2022 Reza Mahjourian, Jinkyu Kim, Yuning Chai, Mingxing Tan, Ben Sapp, Dragomir Anguelov

We propose Occupancy Flow Fields, a new representation for motion forecasting of multiple agents, an important task in autonomous driving.

Motion Estimation Motion Forecasting

GradTail: Learning Long-Tailed Data Using Gradient-based Sample Weighting

no code implementations16 Jan 2022 Zhao Chen, Vincent Casser, Henrik Kretzschmar, Dragomir Anguelov

We propose GradTail, an algorithm that uses gradients to improve model performance on the fly in the face of long-tailed training data distributions.

regression

Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving

no code implementations22 Dec 2021 Jingxiao Zheng, Xinwei Shi, Alexander Gorban, Junhua Mao, Yang song, Charles R. Qi, Ting Liu, Visesh Chari, Andre Cornman, Yin Zhou, CongCong Li, Dragomir Anguelov

3D human pose estimation (HPE) in autonomous vehicles (AV) differs from other use cases in many factors, including the 3D resolution and range of data, absence of dense depth maps, failure modes for LiDAR, relative location between the camera and LiDAR, and a high bar for estimation accuracy.

3D Human Pose Estimation Autonomous Driving

Revisiting 3D Object Detection From an Egocentric Perspective

no code implementations NeurIPS 2021 Boyang Deng, Charles R. Qi, Mahyar Najibi, Thomas Funkhouser, Yin Zhou, Dragomir Anguelov

Given the insight that SDE would benefit from more accurate geometry descriptions, we propose to represent objects as amodal contours, specifically amodal star-shaped polygons, and devise a simple model, StarPoly, to predict such contours.

3D Object Detection Autonomous Driving +2

Lidar Range Image Compression with Deep Delta Encoding

no code implementations29 Sep 2021 Xuanyu Zhou, Charles R. Qi, Yin Zhou, Dragomir Anguelov

However, most prior work focus on the generic point cloud representation, neglecting the spatial patterns of the points from lidar range images.

Autonomous Driving Image Compression +2

Offboard 3D Object Detection from Point Cloud Sequences

no code implementations CVPR 2021 Charles R. Qi, Yin Zhou, Mahyar Najibi, Pei Sun, Khoa Vo, Boyang Deng, Dragomir Anguelov

While current 3D object recognition research mostly focuses on the real-time, onboard scenario, there are many offboard use cases of perception that are largely under-explored, such as using machines to automatically generate high-quality 3D labels.

3D Object Detection 3D Object Recognition +2

Just Pick a Sign: Optimizing Deep Multitask Models with Gradient Sign Dropout

1 code implementation NeurIPS 2020 Zhao Chen, Jiquan Ngiam, Yanping Huang, Thang Luong, Henrik Kretzschmar, Yuning Chai, Dragomir Anguelov

The vast majority of deep models use multiple gradient signals, typically corresponding to a sum of multiple loss terms, to update a shared set of trainable weights.

Transfer Learning

Range Conditioned Dilated Convolutions for Scale Invariant 3D Object Detection

1 code implementation20 May 2020 Alex Bewley, Pei Sun, Thomas Mensink, Dragomir Anguelov, Cristian Sminchisescu

This paper presents a novel 3D object detection framework that processes LiDAR data directly on its native representation: range images.

3D Object Detection Autonomous Driving +1

VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representation

4 code implementations CVPR 2020 Jiyang Gao, Chen Sun, Hang Zhao, Yi Shen, Dragomir Anguelov, Cong-Cong Li, Cordelia Schmid

Behavior prediction in dynamic, multi-agent systems is an important problem in the context of self-driving cars, due to the complex representations and interactions of road components, including moving agents (e. g. pedestrians and vehicles) and road context information (e. g. lanes, traffic lights).

Graph Neural Network Self-Driving Cars

STINet: Spatio-Temporal-Interactive Network for Pedestrian Detection and Trajectory Prediction

no code implementations CVPR 2020 Zhishuai Zhang, Jiyang Gao, Junhua Mao, Yukai Liu, Dragomir Anguelov, Cong-Cong Li

For the Waymo Open Dataset, we achieve a bird-eyes-view (BEV) detection AP of 80. 73 and trajectory prediction average displacement error (ADE) of 33. 67cm for pedestrians, which establish the state-of-the-art for both tasks.

Autonomous Driving object-detection +3

End-to-End Multi-View Fusion for 3D Object Detection in LiDAR Point Clouds

no code implementations15 Oct 2019 Yin Zhou, Pei Sun, Yu Zhang, Dragomir Anguelov, Jiyang Gao, Tom Ouyang, James Guo, Jiquan Ngiam, Vijay Vasudevan

In this paper, we aim to synergize the birds-eye view and the perspective view and propose a novel end-to-end multi-view fusion (MVF) algorithm, which can effectively learn to utilize the complementary information from both.

3D Object Detection object-detection

3D Bounding Box Estimation Using Deep Learning and Geometry

11 code implementations CVPR 2017 Arsalan Mousavian, Dragomir Anguelov, John Flynn, Jana Kosecka

In contrast to current techniques that only regress the 3D orientation of an object, our method first regresses relatively stable 3D object properties using a deep convolutional neural network and then combines these estimates with geometric constraints provided by a 2D object bounding box to produce a complete 3D bounding box.

3D Object Detection Object +4

SSD: Single Shot MultiBox Detector

223 code implementations8 Dec 2015 Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, Alexander C. Berg

Experimental results on the PASCAL VOC, MS COCO, and ILSVRC datasets confirm that SSD has comparable accuracy to methods that utilize an additional object proposal step and is much faster, while providing a unified framework for both training and inference.

LIDAR Semantic Segmentation Low-Light Image Enhancement +4

Self-informed neural network structure learning

no code implementations20 Dec 2014 David Warde-Farley, Andrew Rabinovich, Dragomir Anguelov

We study the problem of large scale, multi-label visual recognition with a large number of possible classes.

Object Recognition

Scalable, High-Quality Object Detection

no code implementations3 Dec 2014 Christian Szegedy, Scott Reed, Dumitru Erhan, Dragomir Anguelov, Sergey Ioffe

Using the multi-scale convolutional MultiBox (MSC-MultiBox) approach, we substantially advance the state-of-the-art on the ILSVRC 2014 detection challenge data set, with $0. 5$ mAP for a single model and $0. 52$ mAP for an ensemble of two models.

Object object-detection +2

Going Deeper with Convolutions

80 code implementations CVPR 2015 Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, Andrew Rabinovich

We propose a deep convolutional neural network architecture codenamed "Inception", which was responsible for setting the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC 2014).

General Classification Image Classification +2

Self-taught Object Localization with Deep Networks

no code implementations13 Sep 2014 Loris Bazzani, Alessandro Bergamo, Dragomir Anguelov, Lorenzo Torresani

This paper introduces self-taught object localization, a novel approach that leverages deep convolutional networks trained for whole-image recognition to localize objects in images without additional human supervision, i. e., without using any ground-truth bounding boxes for training.

Clustering Object +1

Capturing Long-tail Distributions of Object Subcategories

no code implementations CVPR 2014 Xiangxin Zhu, Dragomir Anguelov, Deva Ramanan

We argue that object subcategories follow a long-tail distribution: a few subcategories are common, while many are rare.

Clustering Object

Scalable Object Detection using Deep Neural Networks

6 code implementations CVPR 2014 Dumitru Erhan, Christian Szegedy, Alexander Toshev, Dragomir Anguelov

Deep convolutional neural networks have recently achieved state-of-the-art performance on a number of image recognition benchmarks, including the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC-2012).

Object object-detection +2

Cannot find the paper you are looking for? You can Submit a new open access paper.