Presentation

<
BoostMVSNeRFs: Boosting MVS-based NeRFs to Generalizable View Synthesis in Large-scale Scenes
SessionFast Radiance Fields
DescriptionBoostMVSNeRFs revolutionizes 3D scene visualization by improving the quality of large-scale MVS-based NeRFs. This innovative technique combines multiple cost volumes with 3D visibility scores to enhance novel view synthesis without additional training. Compatible with current frameworks, it sets new 3D reconstruction and visualization standards, offering significant quality and efficiency improvements.
Authors
Chih-Hai Su
National Yang Ming Chiao Tung University
Chih-Yao Hu
National Taiwan University
Shr-Ruei Tsai
National Yang Ming Chiao Tung University
Jie-Ying Lee
National Yang Ming Chiao Tung University
Chin-Yang Lin
National Yang Ming Chiao Tung University
Yu-Lun Liu
National Yang Ming Chiao Tung University
Event Type
Technical Paper
TimeMonday, 29 July 20249:10am - 9:20am MDT
LocationMile High 1
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Monday, 29 July 20249:00am - 10:30am MDTMile High 1
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Geometry
Modeling
Rendering
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Monday
Next PresentationNext PresentationA Hierarchical 3D Gaussian Representation for Real-time Rendering of Very Large Scenes