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

Junyeong Ahn^1*, Geonwoo Kim^2*, Kinam Kim^1*, Gihwi Kim³, Hoonjin Jung³, Hyojin Jang¹, Jaegul Choo¹

¹KAIST AI ²Inha University ³FLIPTION

arXiv Video Code Dataset

Orbit 360°

A snowman in a wizard hat, hugging a small bird on a floating ice block, among glaciers and snow-capped mountains … + [Orbit 360°]

TL;DR: Given a few reference images of an object, OmniShowcase generates a video of that same object along diverse camera paths, even full 360° orbits, keeping its identity and 3D shape consistent by conditioning the video model on a turntable of surface-normal maps reconstructed from the references. We also release Showcase-4K, a training corpus of 3D-asset-based videos covering twelve camera motions across 88 trajectory configurations, and ShowcaseBench, a held-out evaluation set that ships the source meshes and camera parameters behind every video.

Method

Four reference views are reconstructed in 3D and rendered as a surface-normal turntable. References and normals are concatenated with the target span and read in context by a LoRA-tuned image-to-video diffusion transformer.

Automated 3D-consistent data synthesis pipeline — **Data synthesis pipeline.** Blender renders the target orbit and four reference views from one curated 3D asset. The target is composited into a prompt-driven scene, and the four views are reconstructed and rendered as the normal turntable used as the condition.

Architecture overview — **Architecture.** The reference images and the normal condition enter the reference pathway of the diffusion transformer, with no frame-wise alignment between the normal turntable and the generated video.

Beyond the turntable

The normal condition is a fixed yaw sweep, but the generated camera is not bound to it. The target follows whichever trajectory the prompt names.

Arc-Up

The wooden teddy bear statue on a tile ledge of an Amalfi Coast terrace above a turquoise sea … + [Arc-Up]

Comparison with baselines

Same references, same prompt and same trajectory for every method.

ShowcaseBench

Arc-Down

Phantom

MAGREF

MV-S2V

3DreamBooth

Ours

The wooden teddy bear statue on the porch of a snow-covered log cabin at dusk … + [Arc-Down]

NAVI (real-world objects)