Can you generate a video that spins a product or person a full 360° and still keeps it "the same thing"? 🔄 OmniShowcase: Omnidirectional Subject-Consistent Video Generation from Multi-View Images It generates subject-consistent orbit videos from four multi-view reference images. 🧱 Highlight 1: auto-synthesized 3D-consistent data From one 3D mesh, it renders the target orbit and four reference views at 90° intervals. Backgrounds come from video inpainting, with a VLM gating every stage. Curation costs about $120 in total, and the roughly 4,000-video Showcase-4K is planned for release. 📐 Highlight 2: normal maps as in-context input It builds 3D Gaussians from the four references and feeds a normal-map turntable to Wan2.1 via LoRA. No frame-level alignment with the target is needed, and going from one to four references lifts DINO from 0.702 to 0.799. 📊 Highlight 3: a wide margin on 3D metrics On ShowcaseBench versus 3DreamBooth, GT-CD improves from 0.1717 to 0.0824 and MEt3R from 0.325 to 0.190. In the user study it won 70.9–79.4% of votes on each criterion. The takeaway: explicit 3D geometry beats adding more 2D references. Non-rigid subjects remain a weakness. #VideoGeneration# #ComputerVision#