Presentation

<
ArtiFixer: Enhancing and Extending 3D Reconstruction with Auto-Regressive Diffusion Models
SessionReconstruction
DescriptionArtiFixer enhances and extends 3D reconstructions efficiently and scalably. Given an initial reconstruction and reference views, it autoregressive generates novel content consistent with existing observations. ArtiFixer can produce hundreds of novel views in a single inference pass or serve as pseudo-supervision to improve the underlying 3D reconstruction.
Authors
Riccardo De Lutio
NVIDIA
Tobias Fischer
NVIDIA
ETH Zürich
Yen-Yu Chang
NVIDIA
Cornell University
Yuxuan Zhang
NVIDIA
Zhangjie Wu
NVIDIA
Xuanchi Ren
NVIDIA
University of Toronto
Tianchang Shen
NVIDIA
University of Toronto
Katarína Tóthová
NVIDIA
Zan Gojcic
NVIDIA
Haithem Turki
NVIDIA
Event Type
Technical Paper
TimeWednesday, 22 July 202611:45am - 11:55am PDT
LocationRoom 408 B
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Wednesday, 22 July 202610:45am - 12:35pm PDTRoom 408 B
Keywords
Artificial Intelligence/Machine Learning
Generative AI
Rendering
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationReconstruction - Interactive Discussion
Similar Presentations
ViewWeaver: Geometry-Grounded Generative Rendering for 3D-Aware Image Customization
LongE2V: Long-Horizon Event-based Video Reconstruction, Prediction, and Frame Interpolation with Video Diffusion Models
GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction