3D Part Guided Image Editing for Fine-Grained Object Understanding

Liu, Zongdai; Lu, Feixiang; Wang, Peng; Miao, Hui; Zhang, Liangjun; Yang, Ruigang; Zhou, Bin

doi:10.1109/cvpr42600.2020.01135

Cited by 9 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, we use Apollo-Car3D [43] as the existing dataset, which provides the vehicle annotations in the front view. We follow the approach [25] to obtain the rendering data using the 3dsMax software. The GAN-based data is generated by the approach from [28], which can synthesize novel-view vehicles according to the pre-defined poses.…”

Section: Comparison With Data Augmentation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Robust 2D/3D Vehicle Parsing in CVIS

Miao,

Lu,

Liu

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present a novel approach to robustly detect and perceive vehicles in different camera views as part of a cooperative vehicle-infrastructure system (CVIS). Our formulation is designed for arbitrary camera views and makes no assumptions about intrinsic or extrinsic parameters. First, to deal with multi-view data scarcity, we propose a partassisted novel view synthesis algorithm for data augmentation. We train a part-based texture inpainting network in a self-supervised manner. Then we render the textured model into the background image with the target 6-DoF pose. Second, to handle various camera parameters, we present a new method that produces dense mappings between image pixels and 3D points to perform robust 2D/3D vehicle parsing. Third, we build the first CVIS dataset for benchmarking, which annotates more than 1540 images (14017 instances) from real-world traffic scenarios. We combine these novel algorithms and datasets to develop a robust approach for 2D/3D vehicle parsing for CVIS. In practice, our approach outperforms SOTA methods on 2D detection, instance segmentation, and 6-DoF pose estimation, by 4.5%, 4.3%, and 2.9%, respectively. More details and results are included in the supplement. To facilitate future research, we will release the source code and the dataset on GitHub.

show abstract

Section: Comparison With Data Augmentation Methodsmentioning

confidence: 99%

“…Another approach for data augmentation is image editing [25]. Dwibedi et al [10] cut objects from images and then paste them to other backgrounds to synthesize photorealistic training data.…”

Section: Data Augmentationmentioning

confidence: 99%

Robust 2D/3D Vehicle Parsing in CVIS

Miao,

Lu,

Liu

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the 3D domain advances have been made in object understanding when segmenting objects into their parts [28], [29]. In 2D, approaches based on object parts were used for fine-grained object understanding [30], [31].…”

Section: Fine-grained Image Segmentationmentioning

confidence: 99%

A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios

Metzger¹,

Mortimer²,

Wuensche³

2021

Preprint

View full text Add to dashboard Cite

Research in autonomous driving for unstructured environments suffers from a lack of semantically labeled datasets compared to its urban counterpart. Urban and unstructured outdoor environments are challenging due to the varying lighting and weather conditions during a day and across seasons. In this paper, we introduce TAS500, a novel semantic segmentation dataset for autonomous driving in unstructured environments. TAS500 offers fine-grained vegetation and terrain classes to learn drivable surfaces and natural obstacles in outdoor scenes effectively. We evaluate the performance of modern semantic segmentation models with an additional focus on their efficiency. Our experiments demonstrate the advantages of fine-grained semantic classes to improve the overall prediction accuracy, especially along the class boundaries. The dataset and pretrained model are available at mucar3.de/icpr2020-tas500.

show abstract

“…High inter-class similarity of birds at the same taxonomic level, especially at the bird species level, poses a great challenge to CNN models for bird image classification [ 17 ]. To address this problem, several studies have used fine-grained image classification techniques to effectively improve the performance of bird image classification [ 18 , 19 , 20 , 21 , 22 ]. However, the fine-grained image classification task relies on fine-grained manual annotation of physiological parts such as bill, forehead, neck, torso, wings, feet and tail for each bird image.…”

Section: Introductionmentioning

confidence: 99%

Eyebirds: Enabling the Public to Recognize Water Birds at Hand

Jiaogen

Wang

Zhang

et al. 2022

Animals

View full text Add to dashboard Cite

Enabling the public to easily recognize water birds has a positive effect on wetland bird conservation. However, classifying water birds requires advanced ornithological knowledge, which makes it very difficult for the public to recognize water bird species in daily life. To break the knowledge barrier of water bird recognition for the public, we construct a water bird recognition system (Eyebirds) by using deep learning, which is implemented as a smartphone app. Eyebirds consists of three main modules: (1) a water bird image dataset; (2) an attention mechanism-based deep convolution neural network for water bird recognition (AM-CNN); (3) an app for smartphone users. The waterbird image dataset currently covers 48 families, 203 genera and 548 species of water birds worldwide, which is used to train our water bird recognition model. The AM-CNN model employs attention mechanism to enhance the shallow features of bird images for boosting image classification performance. Experimental results on the North American bird dataset (CUB200-2011) show that the AM-CNN model achieves an average classification accuracy of 85%. On our self-built water bird image dataset, the AM-CNN model also works well with classification accuracies of 94.0%, 93.6% and 86.4% at three levels: family, genus and species, respectively. The user-side app is a WeChat applet deployed in smartphones. With the app, users can easily recognize water birds in expeditions, camping, sightseeing, or even daily life. In summary, our system can bring not only fun, but also water bird knowledge to the public, thus inspiring their interests and further promoting their participation in bird ecological conservation.

show abstract

3D Part Guided Image Editing for Fine-Grained Object Understanding

Cited by 9 publications

References 29 publications

Robust 2D/3D Vehicle Parsing in CVIS

Robust 2D/3D Vehicle Parsing in CVIS

A Fine-Grained Dataset and its Efficient Semantic Segmentation for Unstructured Driving Scenarios

Eyebirds: Enabling the Public to Recognize Water Birds at Hand

Contact Info

Product

Resources

About