iQIYI Revives 90-Year-Old Lost Film with NadouPro, Shortlisted for the AI Unit at the Golden Rooster Awards
With no surviving prints or scripts, the team reconstructed the film using production stills, posters and newspaper clippings.
Sentiment and the balance of points
Rhea-AI Sentiment reads the wording of the document, how positive or negative its language is on a 1 to 5 scale. The balance of points shown with the takes weighs what the document actually discloses, so the two can disagree, for example when a trial that missed its main goal is described in upbeat language.
Rhea-AI Summary
iQIYI (IQ) used its NadouPro AI platform to creatively reconstruct a lost film, earning a Golden Rooster Awards AI-unit shortlist place. The project recreates “Visiting Shanghai after Sixty Years,” originally released in 1938, whose physical prints, reels and scripts had been lost. An eight-person team at the iQIYI-XMU Joint Laboratory of Film Restoration completed the work in two months, using production stills, posters and newspaper clippings as conceptual guides rather than restoring surviving footage.
The film was shortlisted for the 2026 Future Images AI Unit at the 39th Golden Rooster Awards. The team used NadouPro's digital character assets and 3D Director Studio to manage visual continuity and shot composition. The project extends iQIYI's film-restoration work into creative reconstruction based on surviving historical materials.
Key Terms
super-resolution technical
frame interpolation technical
AI-generated analysis. How Rhea-AI works. Not financial advice.
Completed by an eight-person team at the iQIYI-XMU Joint Laboratory of Film Restoration in just two months, the project has recently been shortlisted for the "2026 Future Images AI Unit" at the 39th Golden Rooster Awards. The Golden Rooster Awards are among
The Challenge: Building a Movie Without Footage
Traditional film restoration typically relies on surviving film materials, using digital technologies to repair damage and enhance image quality. However, with the original 1938 release of "Visiting Shanghai after Sixty Years" – one of
"NadouPro allowed us to step outside the conventional restoration mindset," said Zidong JIANG, Member of iQIYI-XMU Joint Laboratory and iQIYI's Director of AI Restoration Technology. "With no surviving film prints to restore, we used AI to undertake a creative reconstruction of the film based on available historical materials."
Building a film from the ground up highlighted two major complexities in generative video: maintaining character consistency across scenes and achieving precise camera control. The team utilized NadouPro to address both.
Maintaining Continuity Through Digital Assets
The film spans two distinct historical eras – 1938 and 1998 – and features multiple characters. In generative video, ensuring characters retain the same appearance across different shots is historically difficult.
NadouPro solved this by acting as a centralized production hub. Rather than generating characters anew for every scene, the team used the platform to lock in permanent digital assets for each character's facial features, proportions, and costumes upfront. Subsequent shots drew from these foundational files, keeping character appearances perfectly consistent throughout the film.
Enabling Directorial Control with 3D Director Studio
Recreating acting performances from still photos required high precision. Rather than relying on trial-and-error AI generation, the team used NadouPro's 3D Director Studio to precisely control character positioning, composition, and movement, supported by tools for exploring different scenes, visual styles, and camera angles.
This control ensured filmmakers led the creative direction. The 1938 sequences drew inspiration from early black-and-white cinema with stable cameras and vintage lighting, while the 1998 scenes adopted a documentary style with natural light and handheld camera movement.
"NadouPro helped us move from relatively random image generation toward shots with clear directorial intent," said Enji YANG, the Director of the new film. "In the early stage, we still followed traditional methods: script analysis, character design, scene design, and storyboard planning. We always believe the audiovisual design of a film must come first, before considering how AI can realize it."
Aigong ZHANG, Chief Planner of the new film and Director of the iQIYI-XMU Joint Laboratory, noted that the project demonstrates how AI can integrate into a professional workflow. "NadouPro shares something in common with the production of this short film: the organic integration of traditional filmmaking craftsmanship with AI."
Building on Years of AI Restoration Work
As one of the earliest long-form video platforms to invest in AI film restoration, iQIYI has been exploring the related technology since 2017. Its proprietary ZoomAI uses algorithms for scratch repair, super-resolution, noise reduction, and intelligent frame interpolation, helping shift restoration from manual frame-by-frame work toward automated processes.
Through its joint laboratory with
View original content to download multimedia:https://www.prnewswire.com/news-releases/iqiyi-revives-90-year-old-lost-film-with-nadoupro-shortlisted-for-the-ai-unit-at-the-golden-rooster-awards-302931955.html
SOURCE iQIYI