Presentation

<
MVD^2: Efficient Multiview 3D Reconstruction for Multiview Diffusion
SessionGeometry: Reconstruction
DescriptionMultiview diffusion (MVD) has emerged as a prominent 3D generation technique, but faces challenges with inconsistency and view sparseness, impacting the quality of multiview 3D reconstruction. Our learning-based MVD^2 method tackles these challenges, ensuring efficient and robust 3D reconstruction with superior quality from various multiview diffusion images.
Authors
Xin-Yang Zheng
Tsinghua University
Microsoft Research Asia
Hao Pan
Microsoft Research Asia
Yu-Xiao Guo
Microsoft Research Asia
Xin Tong
Microsoft Research Asia
Yang Liu
Microsoft
Event Type
Technical Paper
TimeMonday, 29 July 20242:00pm - 2:10pm MDT
LocationMile High 2A
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 28 July 20246:00pm - 8:45pm MDTBluebird Ballroom
Monday, 29 July 20242:00pm - 3:30pm MDTMile High 2A
Interest Areas
Research & Education
Recordings
Livestreamed
Recorded
Keywords
Geometry
Modeling
Registration Categories
Full Conference
Full Conference Supporter
Virtual Access
Exhibitor Full Conference
Monday
Next PresentationNext PresentationHigh-quality Surface Reconstruction Using Gaussian Surfels