RdSOBA: Rendered Shadow-Object Association Dataset

06/30/2023
by   Xinhao Tao, et al.
0

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 shadows for the inserted foreground object to make the composite image more realistic. To supplement the existing small-scale dataset DESOBA, we created a large-scale dataset called RdSOBA with 3D rendering techniques. Specifically, we place a group of 3D objects in the 3D scene, and get the images without or with object shadows using controllable rendering techniques. Dataset is available at https://github.com/bcmi/Rendered-Shadow-Generation-Dataset-RdSOBA.

READ FULL TEXT

page 1

page 3

research
08/19/2023

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

Image composition refers to inserting a foreground object into a backgro...
research
07/05/2021

OPA: Object Placement Assessment Dataset

Image composition aims to generate realistic composite image by insertin...
research
08/19/2023

ControlCom: Controllable Image Composition using Diffusion Model

Image composition targets at synthesizing a realistic composite image fr...
research
06/17/2021

A Random CNN Sees Objects: One Inductive Bias of CNN and Its Applications

This paper starts by revealing a surprising finding: without any learnin...
research
09/27/2022

Im2Oil: Stroke-Based Oil Painting Rendering with Linearly Controllable Fineness Via Adaptive Sampling

This paper proposes a novel stroke-based rendering (SBR) method that tra...
research
06/28/2021

Making Images Real Again: A Comprehensive Survey on Deep Image Composition

As a common image editing operation, image composition aims to cut the f...
research
05/28/2022

Fast Object Placement Assessment

Object placement assessment (OPA) aims to predict the rationality score ...

Please sign up or login with your details

Forgot password? Click here to reset