Ovie Monocular Novel View Synthesis

A single insight eliminates multi-view requirements for novel-view synthesis: monocular depth acts as a training-time geometric scaffold to generate synthetic view pairs from unpaired internet images, but can be discarded at inference. This reframes the problem from needing paired multi-view data to leveraging abundant 2D internet imagery. Trigger: When limited to monocular video or single-image novel-view synthesis, use depth as training scaffold on unpaired data—the model learns geometry without needing it at inference.

adu2021 Updated 7 repo stars

File contents

adu2021/skillxiv commit 3b497a5f68

Frequently asked questions

npx get-skill add adu2021/ovie-monocular-novel-view-synthesis