DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation

• URL: http://arxiv.org/abs/2308.09972v1
• Date: Sat, 19 Aug 2023 10:21:23 GMT
• Title: DESOBAv2: Towards Large-scale Real-world Dataset for Shadow Generation
• Authors: Qingyang Liu, Jianting Wang, Li Niu
• Abstract summary: In this work, we focus on generating plausible shadow for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset DESOBA, we create a large-scale dataset called DESOBAv2.
• Score: 19.376935979734714
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Image composition refers to inserting a foreground object into a background image to obtain a composite image. In this work, we focus on generating plausible shadow for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset DESOBA, we create a large-scale dataset called DESOBAv2 by using object-shadow detection and inpainting techniques. Specifically, we collect a large number of outdoor scene images with object-shadow pairs. Then, we use pretrained inpainting model to inpaint the shadow region, resulting in the deshadowed images. Based on real images and deshadowed images, we can construct pairs of synthetic composite images and ground-truth target images. Dataset is available at https://github.com/bcmi/Object-Shadow-Generation-Dataset-DESOBAv2.

Related papers

• MegaScenes: Scene-Level View Synthesis at Scale [69.21293001231993]
  Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics applications. We create a large-scale scene-level dataset from Internet photo collections, called MegaScenes, which contains over 100K structure from motion (SfM) reconstructions from around the world. We analyze failure cases of state-of-the-art NVS methods and significantly improve generation consistency.
  arXiv  Detail & Related papers  (2024-06-17T17:55:55Z)
• Shadow Generation for Composite Image Using Diffusion model [16.316311264197324]
  We resort to foundation model with rich prior knowledge of natural shadow images. We first adapt ControlNet to our task and then propose intensity modulation modules to improve the shadow intensity. Experimental results on both DESOBA and DESOBAv2 datasets as well as real composite images demonstrate the superior capability of our model for shadow generation task.
  arXiv  Detail & Related papers  (2024-03-22T14:27:58Z)
• OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects [56.065616159398324]
  We introduce OpenIllumination, a real-world dataset containing over 108K images of 64 objects with diverse materials. For each image in the dataset, we provide accurate camera parameters, illumination ground truth, and foreground segmentation masks.
  arXiv  Detail & Related papers  (2023-09-14T17:59:53Z)
• Foreground Object Search by Distilling Composite Image Feature [15.771802337102837]
  Foreground object search (FOS) aims to find compatible foreground objects for a given background image. We observe that competitive retrieval performance could be achieved by using a discriminator to predict the compatibility of composite image. We propose a novel FOS method via distilling composite feature (DiscoFOS)
  arXiv  Detail & Related papers  (2023-08-09T14:43:10Z)
• Shadow Generation with Decomposed Mask Prediction and Attentive Shadow Filling [26.780859992812186]
  We focus on generating plausible shadows for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset, we create a large-scale dataset called RdSOBA with rendering techniques. We design a two-stage network named DMASNet with mask prediction and attentive shadow filling.
  arXiv  Detail & Related papers  (2023-06-30T01:32:16Z)
• Scrape, Cut, Paste and Learn: Automated Dataset Generation Applied to Parcel Logistics [58.720142291102135]
  We present a fully automated pipeline to generate a synthetic dataset for instance segmentation in four steps. We first scrape images for the objects of interest from popular image search engines. We compare three different methods for image selection: Object-agnostic pre-processing, manual image selection and CNN-based image selection.
  arXiv  Detail & Related papers  (2022-10-18T12:49:04Z)
• Making Images Real Again: A Comprehensive Survey on Deep Image Composition [34.09380539557308]
  Image composition task could be into multiple sub-tasks, in which each sub-task targets at one or more issues. In this paper, we conduct comprehensive survey over the sub-tasks and blending of image composition. For each one, we summarize the existing methods, available datasets, and common evaluation metrics.
  arXiv  Detail & Related papers  (2021-06-28T09:09:14Z)
• Sparse Pose Trajectory Completion [87.31270669154452]
  We propose a method to learn, even using a dataset where objects appear only in sparsely sampled views. This is achieved with a cross-modal pose trajectory transfer mechanism. Our method is evaluated on the Pix3D and ShapeNet datasets.
  arXiv  Detail & Related papers  (2021-05-01T00:07:21Z)
• Shadow Generation for Composite Image in Real-world Scenes [23.532079444113528]
  We propose a novel shadow generation network SGRNet, which consists of a shadow mask prediction stage and a shadow filling stage. In the shadow mask prediction stage, foreground and background information are thoroughly interacted to generate foreground shadow mask. In the shadow filling stage, shadow parameters are predicted to fill the shadow area.
  arXiv  Detail & Related papers  (2021-04-21T03:30:02Z)
• DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort [117.41383937100751]
  Current deep networks are extremely data-hungry, benefiting from training on large-scale datasets. We show how the GAN latent code can be decoded to produce a semantic segmentation of the image. These generated datasets can then be used for training any computer vision architecture just as real datasets are.
  arXiv  Detail & Related papers  (2021-04-13T20:08:29Z)
• BachGAN: High-Resolution Image Synthesis from Salient Object Layout [78.51640906030244]
  We propose a new task towards more practical application for image generation - high-quality image synthesis from salient object layout. Two main challenges spring from this new task: (i) how to generate fine-grained details and realistic textures without segmentation map input; and (ii) how to create a background and weave it seamlessly into standalone objects. By generating the hallucinated background representation dynamically, our model can synthesize high-resolution images with both photo-realistic foreground and integral background.
  arXiv  Detail & Related papers  (2020-03-26T00:54:44Z)

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.