SOURCE-LINKED INTELLIGENCE

Sparse auto-regressive modeling for scene generation from multi-view images

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Generating complete 3D scenes from sparse, unconstrained views is a fundamental challenge in 3D vision which requires reasoning beyond observed content while remaining computationally tractable. Existing feed-forward reconstruction methods are inherently limited to content visible in the input images, while 3D generative modeling is hindered by the high computational cost of dense volumetric representations and the scarcity of large-scale 3D supervision. We introduce SPAR3S, a sparse voxel-aligned 3D latent generative model for conditional scene completion without requiring ground-truth 3D dat

Read original source ↗ Open in workspace

recordType

paper

region

Global