'Out of the Box' - Synthesizing Historical Fashion for Virtual Production, XR, and Games via Generative Re-imagination and 4DGS

Bringing The Mandalorian and Grogu to Life: Virtual Production, Creatures, and VFX Innovations

Industrial Light & Magic invites you behind the scenes of The Mandalorian and Grogu for an in-depth exploration of the visual effects that brought the latest Star Wars feature to life. In this panel, the filmmakers and artists will unpack how groundbreaking real-time technology, virtual production workflows, and time-tested VFX techniques came together to create immersive worlds, unforgettable characters, and epic action on the big screen. From on-set innovation to final pixels, join the ILM team as they share creative insights, technical breakthroughs, and lessons learned while pushing the boundaries of modern visual storytelling.

Previs to Final Pixels: Rethinking feature animation production in real-time

Dwarf Animation Studio is producing Twisted, an 80-minute animated feature directed by Lino DiSalvo, on a 16-month timeline including pre-production. To meet this schedule without compromising creative ambition, we built a pipeline in which Unreal Engine 5.6 is the final rendering and compositing environment. On our earlier production using Renderman, a single frame took 35 to 60 minutes to render and needed over 200 dedicated render nodes. On Twisted, a fully post-processed 2K frame renders in approximately 3 seconds (Figure 1) on fewer than 10 farm nodes. When render latency becomes negligible, the organizational logic built around managing that latency breaks down. This paper presents the technical systems we built to make this work: a multi-shot lighting workflow on nested Unreal Level Sequences with automatic shot group generation; a dual-format animation pipeline combining FBX and Alembic with per-asset tagging and a data-driven Blueprint architecture; a modified USD exporter that outputs environment data once per sequence with lightweight per-shot override files; a painterly look development pipeline built on custom shaders; and a performance strategy within a hard 16 GB VRAM limit on an RTX 5080. It also presents, with equal candor, what broke: the collision between departments that simultaneous data access made inevitable, and the organizational friction of migrating artists from a centralized network-drive pipeline to a version-controlled local workflow.

From Pixel to Mesh: Accelerating Game Asset Creation via a Semantically-Guided 2D-to-3D Generative Pipeline

In independent game development, creating high-quality 3D assets remains a critical bottleneck, as traditional workflows require specialized skills that hinder non-expert designers. While Generative AI has democratized 2D concept art, translating these visions into game-ready 3D assets is technically demanding. To address this, we propose an automated pipeline that leverages semantic and geometric feature extraction to synthesize 3D meshes and PBR materials from AI-generated 2D images. Our system orchestrates a workflow bridging text-to-image diffusion models with advanced computer vision modules. It employs monocular depth estimation and intrinsic decomposition to interpret geometric structures and isolate material properties (albedo, roughness, metallic) from multi-view consistent concepts. These features are algorithmically processed to produce finalized .glb assets. A comparative user study with indie developers demonstrates that this pipeline reduces asset production time by approximately 80% compared to traditional modeling tools. By shifting the user’s role from manual vertex manipulation to high-level semantic curation, this research validates a novel workflow that empowers designers to rapidly populate immersive worlds, streamlining the future of interactive media design.

From Front-End to Final Frames: Building a 2D/3D Hybrid Back-End Pipeline for Feature Animation at Scale

Paramount Animation has historically operated as a front-end creative studio, partnering with external vendors to execute CG workflows through final delivery. For “Avatar Aang: The Last Airbender,” the production demanded a hybrid visual style—blending CG rendering, 2D hand-drawn animation, and 2.5D projection-based treatments—that no vendor could deliver end-to-end under the tight production schedule. We stood up an entirely new internal back-end pipeline spanning ingest, compositing, effects, layout, and rendering in under five months with a 5-person TD team supporting 62 artists at a studio with no prior back-end experience. This paper presents FLO, a USD-to-Nuke assembly system; vendor-aware ingest validation; Nuke-side tooling for path-agnostic compositing, hand-drawn timing, and shot localization; Houdini USD FX integration; and Deadline render-farm automation. We report results across ∼ 1, 500 shots and share tradeoffs and lessons learned.

infinity and back again: hand-drawn aesthetic and affection for the past in Pixar's pioneering animation

Generative AI-Assisted Visualization Prototyping for Cultural Heritage: A Computational Framework from 2D Planes to 3D Immersive Scenes

A human-in-the-loop GenAI-assisted framework for producing immersive 3D visualization prototypes rather than historically verified reconstructions is proposed, which integrates multi-view image generation, knowledge-informed review, single-image-to-3D generation, topology inspection, and perceptual calibration.