Sparse Auto-regressive Modeling for Scene Generation from Multi-view Images
Authors:
- Thomas LucasTLThomas Lucas
- Maxime PietrantoniMPMaxime Pietrantoni
- Philippe WeinzaepfelPWPhilippe Weinzaepfel
- Bardienus Pieter DuisterhofBDBardienus Pieter Duisterhof
- Vincent LeroyVLVincent Leroy
- 4 October 2026
- book chapter
- Published by Springer Nature
- p. 147-165
Abstract
No abstract availableKeywords
All Related Versions
This publication has 43 references indexed in Scilit:
- MASt3R-SfM: A Fully-Integrated Solution for Unconstrained Structure-from-Motion2025
- 3D Reconstruction with Spatial Memory2025
- Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image2025
- GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation2024
- LatentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction2024
- Grounding Image Matching in 3D with MASt3R2024
- MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-view Images2024
- LGM: Large Multi-view Gaussian Model for High-Resolution 3D Content Creation2024
- GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting2024
- The Unreasonable Effectiveness of Deep Features as a Perceptual Metric2018