Joint Learning of Intrinsic Images and Semantic Segmentation

Baslamisli, Anil S.; Groenestege, Thomas T.; Das, Partha; Le, Hoang-An; Karaoğlu, Sezer; Gevers, Theo

doi:10.1007/978-3-030-01231-1_18

Cited by 47 publications

(45 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the same spirit, Baslamisli et al . [BGD*18] present a data generation method for natural images of flora, utilizing procedural physically based modelling, suitable to learn both intrinsic image decomposition and semantic segmentation (Figure 15b). Finally, Sial et al .…”

Section: Image Synthesis Methods Overviewmentioning

confidence: 99%

A Survey of Image Synthesis Methods for Visual Machine Learning

Tsirikoglou

Eilertsen

Unger

2020

Computer Graphics Forum

View full text Add to dashboard Cite

Image synthesis designed for machine learning applications provides the means to efficiently generate large quantities of training data while controlling the generation process to provide the best distribution and content variety. With the demands of deep learning applications, synthetic data have the potential of becoming a vital component in the training pipeline. Over the last decade, a wide variety of training data generation methods has been demonstrated. The potential of future development calls to bring these together for comparison and categorization. This survey provides a comprehensive list of the existing image synthesis methods for visual machine learning. These are categorized in the context of image generation, using a taxonomy based on modelling and rendering, while a classification is also made concerning the computer vision applications they are used. We focus on the computer graphics aspects of the methods, to promote future image generation for machine learning. Finally, each method is assessed in terms of quality and reported performance, providing a hint on its expected learning potential. The report serves as a comprehensive reference, targeting both groups of the applications and data development sides. A list of all methods and papers reviewed herein can be found at https://computergraphics.on.liu.se/image_synthesis_methods_for_visual_machine_learning/.

show abstract

Section: Image Synthesis Methods Overviewmentioning

confidence: 99%

A Survey of Image Synthesis Methods for Visual Machine Learning

Tsirikoglou

Eilertsen

Unger

2020

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…An image can be decomposed to generate countless combinations of reflectance and illumination, so image decomposition is a long-standing ill-posed problem [23]. Li et al [24] add nonlocal texture constraints to traditional techniques to optimize intrinsic image decomposition, which is a significant improvement over previous algorithms.…”

Section: Intrinsic Image Decompositionmentioning

confidence: 99%

A Mechanical Parts Image Segmentation Method Against Illumination for Industry

Xie¹,

Wan²,

Wang³

et al. 2020

Preprint

View full text Add to dashboard Cite

Most of the current image edge detection methods rely on manually features to extract the edge, there are often false and missed detections when the image has adverse interference. The surface of mechanical parts is smooth, when taking photos in the industrial field, it is easy to have specular reflection and shadow at the same time, which will affect the edge detection results. In order to achieve excellent edge detection performance, we propose a semantic segmentation model based on encoder-decoder structure. It adopts joint learning strategy, using two decoders to process image decomposition task and segmentation task respectively, and sharing their parameters to eliminate the influence of illumination, so as to improve segmentation performance. In the training phase, the asymmetric convolution and BN fusion are combined to improve the detection efficiency. In addition, we built a gear part dataset for experimentation. The result shows that in the task of edge detection of mechanical parts affected by illumination, our method has better performance than classical method.

show abstract

“…reconstruction [30], or intrinsic properties estimation [31]. Compared to these works, our proposed method is an endto-end solution to perform segmentation and curvature estimation (that, as far as we are concerned, was not proposed before), for which each module is trained with different datasets.…”

Section: Related Workmentioning

confidence: 99%

Terrain Segmentation and Roughness Estimation using RGB Data: Path Planning Application on the CENTAURO Robot

Suryamurthy

Raghavan

Laurenzi

et al. 2019

2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids)

View full text Add to dashboard Cite

Robots operating in real world environments require a high-level perceptual understanding of the chief physical properties of the terrain they are traversing. In unknown environments, roughness is one such important terrain property that could play a key role in devising robot control/planning strategies. In this paper, we present a fast method for predicting pixel-wise labels of terrain (stone, sand, road/sidewalk, wood, grass, metal) and roughness estimation, using a single RGBbased deep neural network. Real world RGB images are used to experimentally validate the presented approach. Furthermore, we demonstrate an application of our proposed method on the centaur-like wheeled-legged robot CENTAURO, by integrating it with a navigation planner that is capable of re-configuring the leg joints to modify the robot footprint polygon for stability purposes or for safe traversal among obstacles.

show abstract

Joint Learning of Intrinsic Images and Semantic Segmentation

Cited by 47 publications

References 37 publications

A Survey of Image Synthesis Methods for Visual Machine Learning

A Survey of Image Synthesis Methods for Visual Machine Learning

A Mechanical Parts Image Segmentation Method Against Illumination for Industry

Terrain Segmentation and Roughness Estimation using RGB Data: Path Planning Application on the CENTAURO Robot

Contact Info

Product

Resources

About