IMPROVING NOVEL VIEW SYNTHESIS OF 360 SCENES IN EXTREMELY SPARSE VIEWS BY JOINTLY TRAINING HEMISPHERE SAMPLED SYNTHETIC IMAGES

  • Guangan Chen
  • , Anh Minh Truong
  • , Hanhe Lin
  • , Michiel Vlaminck
  • , Wilfried Philips
  • , Hiep Luong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

56 Downloads (Pure)

Abstract

Novel view synthesis in 360 scenes from extremely sparse input views is essential for applications like virtual reality and augmented reality. This paper presents a novel framework for novel view synthesis in extremely sparse-view cases. As typical structure-from-motion methods are unable to estimate camera poses in extremely sparse-view cases, we apply DUSt3R to estimate camera poses and generate a dense point cloud. Using the poses of estimated cameras, we densely sample additional views from the upper hemisphere space of the scenes, from which we render synthetic images together with the point cloud. Training 3D Gaussian Splatting model on a combination of reference images from sparse views and densely sampled synthetic images allows a larger scene coverage in 3D space, addressing the overfitting challenge due to the limited input in sparse-view cases. Retraining a diffusion-based image enhancement model on our created dataset, we further improve the quality of the point-cloud-rendered images by removing artifacts. We compare our framework with benchmark methods in cases of only four input views, demonstrating significant improvement in novel view synthesis under extremely sparse-view conditions for 360 scenes.

Original languageEnglish
Title of host publication2025 IEEE International Conference on Image Processing, ICIP 2025 - Proceedings
Place of PublicationUSA
PublisherIEEE
Pages821-826
Number of pages6
ISBN (Electronic)9798331523794
ISBN (Print)9798331523800
DOIs
Publication statusPublished - 18 Aug 2025
Event32nd IEEE International Conference on Image Processing, ICIP 2025 - Anchorage, United States
Duration: 14 Sept 202517 Sept 2025

Publication series

NameProceedings - International Conference on Image Processing, ICIP
ISSN (Print)1522-4880
ISSN (Electronic)2381-8549

Conference

Conference32nd IEEE International Conference on Image Processing, ICIP 2025
Country/TerritoryUnited States
CityAnchorage
Period14/09/2517/09/25

Keywords

  • 360 scenes
  • 3D Gaussian Splatting
  • diffusion model
  • extremely sparse views
  • image enhancement

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'IMPROVING NOVEL VIEW SYNTHESIS OF 360 SCENES IN EXTREMELY SPARSE VIEWS BY JOINTLY TRAINING HEMISPHERE SAMPLED SYNTHETIC IMAGES'. Together they form a unique fingerprint.

Cite this