Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Image

• URL: http://arxiv.org/abs/2105.07174v1
• Date: Sat, 15 May 2021 08:45:20 GMT
• Title: Stacked Deep Multi-Scale Hierarchical Network for Fast Bokeh Effect Rendering from a Single Image
• Authors: Saikat Dutta, Sourya Dipta Das, Nisarg A. Shah, Anil Kumar Tiwari
• Abstract summary: The Bokeh Effect is one of the most desirable effects in photography for rendering artistic and aesthetic photos. In this paper, we used an end-to-end Deep Multi-Scale Hierarchical Network (DMSHN) model for direct Bokeh effect rendering of images captured from the monocular camera. Stacked DMSHN achieves state-of-the-art results on a large scale EBB! dataset with around 6x less runtime compared to the current state-of-the-art model in processing HD quality images.
• Score: 9.010261475120627
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The Bokeh Effect is one of the most desirable effects in photography for rendering artistic and aesthetic photos. Usually, it requires a DSLR camera with different aperture and shutter settings and certain photography skills to generate this effect. In smartphones, computational methods and additional sensors are used to overcome the physical lens and sensor limitations to achieve such effect. Most of the existing methods utilized additional sensor's data or pretrained network for fine depth estimation of the scene and sometimes use portrait segmentation pretrained network module to segment salient objects in the image. Because of these reasons, networks have many parameters, become runtime intensive and unable to run in mid-range devices. In this paper, we used an end-to-end Deep Multi-Scale Hierarchical Network (DMSHN) model for direct Bokeh effect rendering of images captured from the monocular camera. To further improve the perceptual quality of such effect, a stacked model consisting of two DMSHN modules is also proposed. Our model does not rely on any pretrained network module for Monocular Depth Estimation or Saliency Detection, thus significantly reducing the size of model and run time. Stacked DMSHN achieves state-of-the-art results on a large scale EBB! dataset with around 6x less runtime compared to the current state-of-the-art model in processing HD quality images.

Related papers

• Inverting the Imaging Process by Learning an Implicit Camera Model [73.81635386829846]
  This paper proposes a novel implicit camera model which represents the physical imaging process of a camera as a deep neural network. We demonstrate the power of this new implicit camera model on two inverse imaging tasks.
  arXiv  Detail & Related papers  (2023-04-25T11:55:03Z)
• Bokeh Rendering Based on Adaptive Depth Calibration Network [13.537088629080122]
  Bokeh rendering is a popular technique used in photography to create an aesthetically pleasing effect. Mobile phones are not able to capture natural shallow depth-of-field photos. We propose a novel method for bokeh rendering using the Vision Transformer, a recent and powerful deep learning architecture.
  arXiv  Detail & Related papers  (2023-02-21T16:33:51Z)
• Robustifying the Multi-Scale Representation of Neural Radiance Fields [86.69338893753886]
  We present a robust multi-scale neural radiance fields representation approach to overcome both real-world imaging issues. Our method handles multi-scale imaging effects and camera-pose estimation problems with NeRF-inspired approaches. We demonstrate, with examples, that for an accurate neural representation of an object from day-to-day acquired multi-view images, it is crucial to have precise camera-pose estimates.
  arXiv  Detail & Related papers  (2022-10-09T11:46:45Z)
• Learning Depth from Focus in the Wild [16.27391171541217]
  We present a convolutional neural network-based depth estimation from single focal stacks. Our method allows depth maps to be inferred in an end-to-end manner even with image alignment. For the generalization of the proposed network, we develop a simulator to realistically reproduce the features of commercial cameras.
  arXiv  Detail & Related papers  (2022-07-20T05:23:29Z)
• Facial Depth and Normal Estimation using Single Dual-Pixel Camera [81.02680586859105]
  We introduce a DP-oriented Depth/Normal network that reconstructs the 3D facial geometry. It contains the corresponding ground-truth 3D models including depth map and surface normal in metric scale. It achieves state-of-the-art performances over recent DP-based depth/normal estimation methods.
  arXiv  Detail & Related papers  (2021-11-25T05:59:27Z)
• HDRUNet: Single Image HDR Reconstruction with Denoising and Dequantization [39.82945546614887]
  We propose a novel learning-based approach using a spatially dynamic encoder-decoder network, HDRUNet, to learn an end-to-end mapping for single image HDR reconstruction. Our method achieves the state-of-the-art performance in quantitative comparisons and visual quality.
  arXiv  Detail & Related papers  (2021-05-27T12:12:34Z)
• Wide-angle Image Rectification: A Survey [86.36118799330802]
  wide-angle images contain distortions that violate the assumptions underlying pinhole camera models. Image rectification, which aims to correct these distortions, can solve these problems. We present a detailed description and discussion of the camera models used in different approaches. Next, we review both traditional geometry-based image rectification methods and deep learning-based methods.
  arXiv  Detail & Related papers  (2020-10-30T17:28:40Z)
• Neural Ray Surfaces for Self-Supervised Learning of Depth and Ego-motion [51.19260542887099]
  We show that self-supervision can be used to learn accurate depth and ego-motion estimation without prior knowledge of the camera model. Inspired by the geometric model of Grossberg and Nayar, we introduce Neural Ray Surfaces (NRS), convolutional networks that represent pixel-wise projection rays. We demonstrate the use of NRS for self-supervised learning of visual odometry and depth estimation from raw videos obtained using a wide variety of camera systems.
  arXiv  Detail & Related papers  (2020-08-15T02:29:13Z)
• Rendering Natural Camera Bokeh Effect with Deep Learning [95.86933125733673]
  Bokeh is an important artistic effect used to highlight the main object of interest on the photo. Mobile cameras are unable to produce shallow depth-of-field photos due to a very small aperture diameter of their optics. We propose to learn a realistic shallow focus technique directly from the photos produced by DSLR cameras.
  arXiv  Detail & Related papers  (2020-06-10T07:28:06Z)

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.