RealMaster: Lifting Rendered Scenes into Photorealistic Video

TL;DR

RealMaster is a novel method that enhances rendered 3D scene videos into photorealistic videos by leveraging diffusion models, ensuring geometric consistency and high visual quality without requiring anchor frames.

Contribution

The paper introduces a pipeline combining geometric conditioning and diffusion models to lift rendered videos into photorealistic videos, with a trained IC-LoRA model that generalizes beyond the initial pipeline constraints.

Findings

Outperforms existing video editing baselines on GTA-V sequences

Maintains geometry, dynamics, and identity during enhancement

Enables photorealistic video generation without anchor frames

Abstract

State-of-the-art video generation models produce remarkable photorealism, but they lack the precise control required to align generated content with specific scene requirements. Furthermore, without an underlying explicit geometry, these models cannot guarantee 3D consistency. Conversely, 3D engines offer granular control over every scene element and provide native 3D consistency by design, yet their output often remains trapped in the "uncanny valley". Bridging this sim-to-real gap requires both structural precision, where the output must exactly preserve the geometry and dynamics of the input, and global semantic transformation, where materials, lighting, and textures must be holistically transformed to achieve photorealism. We present RealMaster, a method that leverages video diffusion models to lift rendered video into photorealistic video while maintaining full alignment with the output of the 3D engine. To train this model, we generate a paired dataset via an anchor-based propagation strategy, where the first and last frames are enhanced for realism and propagated across the intermediate frames using geometric conditioning cues. We then train an IC-LoRA on these paired videos to distill the high-quality outputs of the pipeline into a model that generalizes beyond the pipeline's constraints, handling objects and characters that appear mid-sequence and enabling inference without requiring anchor frames. Evaluated on complex GTA-V sequences, RealMaster significantly outperforms existing video editing baselines, improving photorealism while preserving the geometry, dynamics, and identity specified by the original 3D control.