Presentation

<
Splat and Replace: 3D Reconstruction with Repetitive Elements
SessionReconstruct it All
DescriptionWe leverage repetitions in 3D scenes to improve reconstruction in low-quality parts due to poor coverage and occlusions. Our methods segments the repetitions, registers them together, and optimizes a shared representation with multi-view information flowing from all repetitions, improving the reconstruction of each individual repetition.
Authors
Nicolas Violante
INRIA, Université Côte d'Azur
Andréas Meuleman
INRIA, Université Côte d'Azur
Alban Gauthier
INRIA, Université Côte d'Azur
Fredo Durand
Massachusetts Institute of Technology (MIT)
Thibault Groueix
Adobe Research
George Drettakis
INRIA, Université Côte d'Azur
Event Type
Technical Paper
TimeMonday, 11 August 202510:45am - 10:55am PDT
LocationWest Building, Rooms 301-305
ACM Digital Library Journal Papers' PDFs
Conference Papers' PDFs
Session Time & Location
Sunday, 10 August 20256:00pm - 8:45pm PDTWest Building, Ballroom AB
Monday, 11 August 202510:45am - 12:15pm PDTWest Building, Rooms 301-305
Recordings
Livestreamed
Recorded
Next PresentationNext PresentationSpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting
Similar Presentations
On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images
IMLS-Splatting: Efficient Mesh Reconstruction from Multi-view Images via Point Representation
CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image