---
format: "aidr-story-markdown/v1"
id: "7aea845ef70d28b3d9c08292a6b21c34a299d81464548c3bd48372c065dd1780"
canonical_url: "https://aidr.today/7aea845e?lang=en"
title: "OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-29T00:00:00.000Z"
category: "Research"
topics: ["research"]
source_urls: ["https://huggingface.co/papers/2610.35684"]
summary: "Researchers have developed OmniShowcase, a method for generating omnidirectional, subject-consistent videos from multi-view images. The approach uses a fully automated data synthesis pipeline and a geometry-conditioning method that provides surface-normal maps reconstructed from reference views without requiring temporal alignment with generated frames."
---

# OmniShowcase: Omnidirectional Subject\-Consistent Video Generation from Multi\-View Images

> [Open the canonical story](<https://aidr.today/7aea845e?lang=en>)

**Published:** 2026-10-29T00:00:00.000Z
**Category:** Research
**Topics:** research

## Summary

Researchers have developed OmniShowcase, a method for generating omnidirectional, subject\-consistent videos from multi\-view images\. The approach uses a fully automated data synthesis pipeline and a geometry\-conditioning method that provides surface\-normal maps reconstructed from reference views without requiring temporal alignment with generated frames\.

## Sources

- [Story source](<https://huggingface.co/papers/2610.35684>)