VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identification

• URL: http://arxiv.org/abs/2311.16278v3
• Date: Wed, 17 Apr 2024 17:58:59 GMT
• Title: VehicleGAN: Pair-flexible Pose Guided Image Synthesis for Vehicle Re-identification
• Authors: Baolu Li, Ping Liu, Lan Fu, Jinlong Li, Jianwu Fang, Zhigang Xu, Hongkai Yu,
• Abstract summary: This paper proposes to synthesize a large number of vehicle images in the target pose. Considering the paired data of the same vehicles in different traffic surveillance cameras might be not available in the real world, we propose VehicleGAN. Because of the feature distribution difference between real and synthetic data, we propose a new Joint Metric Learning (JML) via effective feature-level fusion.
• Score: 27.075761782915496
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vehicle Re-identification (Re-ID) has been broadly studied in the last decade; however, the different camera view angle leading to confused discrimination in the feature subspace for the vehicles of various poses, is still challenging for the Vehicle Re-ID models in the real world. To promote the Vehicle Re-ID models, this paper proposes to synthesize a large number of vehicle images in the target pose, whose idea is to project the vehicles of diverse poses into the unified target pose so as to enhance feature discrimination. Considering that the paired data of the same vehicles in different traffic surveillance cameras might be not available in the real world, we propose the first Pair-flexible Pose Guided Image Synthesis method for Vehicle Re-ID, named as VehicleGAN in this paper, which works for both supervised and unsupervised settings without the knowledge of geometric 3D models. Because of the feature distribution difference between real and synthetic data, simply training a traditional metric learning based Re-ID model with data-level fusion (i.e., data augmentation) is not satisfactory, therefore we propose a new Joint Metric Learning (JML) via effective feature-level fusion from both real and synthetic data. Intensive experimental results on the public VeRi-776 and VehicleID datasets prove the accuracy and effectiveness of our proposed VehicleGAN and JML.

Related papers

• Multi-query Vehicle Re-identification: Viewpoint-conditioned Network, Unified Dataset and New Metric [30.344288906037345]
  We propose a more realistic and easily accessible task, called multi-query vehicle Re-ID. We design a novel viewpoint-conditioned network (VCNet), which adaptively combines the complementary information from different vehicle viewpoints. Second, we create a unified benchmark dataset, taken by 6142 cameras from a real-life transportation surveillance system. Third, we design a new evaluation metric, called mean cross-scene precision (mCSP), which measures the ability of cross-scene recognition.
  arXiv  Detail & Related papers  (2023-05-25T06:22:03Z)
• Benchmarking the Robustness of LiDAR-Camera Fusion for 3D Object Detection [58.81316192862618]
  Two critical sensors for 3D perception in autonomous driving are the camera and the LiDAR. fusing these two modalities can significantly boost the performance of 3D perception models. We benchmark the state-of-the-art fusion methods for the first time.
  arXiv  Detail & Related papers  (2022-05-30T09:35:37Z)
• Discriminative-Region Attention and Orthogonal-View Generation Model for Vehicle Re-Identification [7.5366501970852955]
  Multiple challenges hamper the applications of vision-based vehicle Re-ID methods. The proposed DRA model can automatically extract the discriminative region features, which can distinguish similar vehicles. And the OVG model can generate multi-view features based on the input view features to reduce the impact of viewpoint mismatches.
  arXiv  Detail & Related papers  (2022-04-28T07:46:03Z)
• Multi-Modal Fusion Transformer for End-to-End Autonomous Driving [59.60483620730437]
  We propose TransFuser, a novel Multi-Modal Fusion Transformer, to integrate image and LiDAR representations using attention. Our approach achieves state-of-the-art driving performance while reducing collisions by 76% compared to geometry-based fusion.
  arXiv  Detail & Related papers  (2021-04-19T11:48:13Z)
• Fine-Grained Vehicle Perception via 3D Part-Guided Visual Data Augmentation [77.60050239225086]
  We propose an effective training data generation process by fitting a 3D car model with dynamic parts to vehicles in real images. Our approach is fully automatic without any human interaction. We present a multi-task network for VUS parsing and a multi-stream network for VHI parsing.
  arXiv  Detail & Related papers  (2020-12-15T03:03:38Z)
• Discriminative Feature Representation with Spatio-temporal Cues for Vehicle Re-identification [0.0]
  Vehicle-identification (re-ID) aims to discover and match the target vehicles from a gallery image set taken by different cameras on a wide range of road networks. We propose a feature representation with novel clues (DFR-ST) for vehicle re-ID. It is capable of building robust features in the embedding space by involving appearance and retemporal information.
  arXiv  Detail & Related papers  (2020-11-13T10:50:21Z)
• PerMO: Perceiving More at Once from a Single Image for Autonomous Driving [76.35684439949094]
  We present a novel approach to detect, segment, and reconstruct complete textured 3D models of vehicles from a single image. Our approach combines the strengths of deep learning and the elegance of traditional techniques. We have integrated these algorithms with an autonomous driving system.
  arXiv  Detail & Related papers  (2020-07-16T05:02:45Z)
• PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data [34.66187690224724]
  Vehicle ReID is challenging due to 1) high intra-class variability (caused by the dependency of shape and appearance on viewpoint), and 2) small inter-class variability (caused by the similarity in shape and appearance between vehicles produced by different manufacturers) We propose a Pose-Aware Multi-Task Re-Identification (PAMTRI) framework. It overcomes viewpoint-dependency by explicitly reasoning about vehicle pose and shape via keypoints, heatmaps and segments from pose estimation. It jointly classifies semantic vehicle attributes (colors and types) while performing ReID, through multi-task learning with the embedded pose representations.
  arXiv  Detail & Related papers  (2020-05-02T01:29:09Z)
• VehicleNet: Learning Robust Visual Representation for Vehicle Re-identification [116.1587709521173]
  We propose to build a large-scale vehicle dataset (called VehicleNet) by harnessing four public vehicle datasets. We design a simple yet effective two-stage progressive approach to learning more robust visual representation from VehicleNet. We achieve the state-of-art accuracy of 86.07% mAP on the private test set of AICity Challenge.
  arXiv  Detail & Related papers  (2020-04-14T05:06:38Z)
• The Devil is in the Details: Self-Supervised Attention for Vehicle Re-Identification [75.3310894042132]
  Self-supervised Attention for Vehicle Re-identification (SAVER) is a novel approach to effectively learn vehicle-specific discriminative features. We show that SAVER improves upon the state-of-the-art on challenging VeRi, VehicleID, Vehicle-1M and VERI-Wild datasets.
  arXiv  Detail & Related papers  (2020-04-14T02:24:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.