Realistic Pedestrian Shadow Generation by 2D-to-3D Object-Lifting

Yu Sheng Su*, Jen Jee Chen, Yu Chee Tseng

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper studies the shadow generation problem in an outdoor street scene. Previous methods only rely on GAN-based model with the sun position to reconstruct the street view. Lacking in related dataset, we propose an evaluation method to make sure of the effectiveness. Our model applies a 2D-to-3D lifting method, casts the 3D object with sun estimation, and finally merges the shadow with a predicted sun brightness. Limited with lifting objects, our model casts more precise shadows than GAN-based model. Tuning with the brightness, the cast shadow will be in consistence with the whole street view. Then in our evaluation, we demonstrate better performance over the state-of-the-art models by 0.009 in LPIPS. Therefore, casting with a 3D human object is a feasible solution for shadow generation in the future.

Original languageEnglish
Title of host publicationProceedings - 2023 VTS Asia Pacific Wireless Communications Symposium, APWCS 2023
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350316803
DOIs
StatePublished - 2023
Event2023 VTS Asia Pacific Wireless Communications Symposium, APWCS 2023 - Tainan City, Taiwan
Duration: 23 Aug 202325 Aug 2023

Publication series

NameProceedings - 2023 VTS Asia Pacific Wireless Communications Symposium, APWCS 2023

Conference

Conference2023 VTS Asia Pacific Wireless Communications Symposium, APWCS 2023
Country/TerritoryTaiwan
CityTainan City
Period23/08/2325/08/23

Keywords

  • Human Synthesis
  • Object Lifting
  • Outdoor Scene Synthesis
  • Shadow Generation

Fingerprint

Dive into the research topics of 'Realistic Pedestrian Shadow Generation by 2D-to-3D Object-Lifting'. Together they form a unique fingerprint.

Cite this