SOURCE-LINKED INTELLIGENCE

Filling the Unseen: Scene Extrapolation via 3D Gaussian Splatting

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

3D Gaussian Splatting achieves photorealistic reconstruction within training view distribution, yet it degrades on out-of-distribution novel views, exhibiting holes in unobserved regions and artifacts in observable areas. Recent works formulate this task as extrapolation and interpolation and try to address it with generative models, but remain limited in extrapolation scale and quality. They repeat a generate-reconstruct-shift cycle to progressively build a scene, which introduces accumulated errors with every step conditioning on previous outcomes. In this work, we propose a holistic framewo

Read original source ↗ Open in workspace

recordType

paper

region

Global