Story2BoardStory2Board
film-theory

The GEST-Engine: event graphs as a storyboard control layer

Story2Board Team··15 min read
The GEST-Engine: event graphs as a storyboard control layer

The GEST-Engine is not a photorealistic video model. That is exactly why it is useful.

The paper describes a system that takes a formal Graph of Events in Space and Time, grounds it inside a controllable game world, and captures multi-actor video with dense annotations. Instead of asking a neural model to remember who is holding what, the system keeps that state explicit. Instead of hoping two actors coordinate correctly, it schedules their events. Instead of labeling video afterward, it captures labels while the world runs.

For Story2Board, this is the important lesson: a storyboard should not be only a stack of generated images. It should also have an event graph underneath it.

GEST-Engine cover showing an event graph becoming a multi-actor simulation and synchronized annotations.

The paper in one sentence

The GEST-Engine turns natural-language or procedurally generated event graphs into deterministic multi-actor simulation videos, while exporting frame-aligned labels such as depth, segmentation, pose, spatial relations, event timing, and captions.

That is a different goal from text-to-video generation. A text-to-video model tries to sample plausible pixels. The GEST-Engine tries to make every frame traceable back to a semantic specification.

The paper argues that this explicit world model gives three properties that implicit video models still struggle with:

PropertyWhy explicit state helps
Object permanencethe system knows which object exists and who holds it
Multi-actor coordinationactors are scheduled through explicit temporal constraints
Temporal consistencyevery event has a position in the story graph and frame timeline

Those three properties are also the hard parts of storyboard continuity.

A video starts as a graph

The core representation is GEST: a Graph of Events in Space and Time. A GEST is a structured story specification. It says which actors exist, which objects exist, where things happen, which actions occur, and how events relate to one another.

That graph is not a prompt. It is closer to a production contract.

Diagram showing actors, objects, actions, locations, and temporal edges inside a Graph of Events in Space and Time.

In a storyboard workflow, this matters because many visual mistakes are not image mistakes. They are state mistakes.

Storyboard failureGraph-level cause
A cup disappears between panelsprop state was not tracked
Two actors swap positionsblocking was not anchored
A reaction happens before the actiontemporal order was underspecified
A door changes side of the roomlocation state was not persistent
A character holds a phone in one shot and nothing in the nextobject possession was not part of the shot contract

The GEST-Engine solves these problems in a simulation setting. Story2Board does not need to copy the game-engine stack, but it should copy the principle: keep semantic state outside the pixels.

The pipeline has four hard boundaries

The system turns a GEST into video through four stages:

StageJob
Graph parsing and validationread the GEST, check requirements, select valid episodes
Entity and action groundingbind abstract actors, objects, and actions to concrete simulator entities
Temporal orchestrationresolve before, after, and same-time constraints into executable segments
Execution and capturerun actions in the game engine and collect aligned artifacts

Four-stage pipeline from graph parsing to grounding, temporal orchestration, execution, and artifact capture.

This separation is practical. The system does not let the story generator directly poke the simulator. It validates the story first. It grounds entities second. It schedules time third. Only then does it execute.

That is the same shape a serious storyboard agent needs. Gemini, the Story2Board co-director, can plan a shot, but the plan should pass through a structured state layer before image generation:

Story2Board layerEquivalent GEST idea
Script beat extractionevent graph creation
Character and prop cardsentity declarations
Shot planaction and camera intent
Continuity checksgraph validation
Panel generationexecution and capture

The takeaway is not that Story2Board should become GTA San Andreas. The takeaway is that a story generation system should have a formal checkpoint before rendering.

Temporal orchestration is the part most tools skip

The paper's temporal system is more interesting than it first sounds. The GEST supports relations such as before, after, and same_time, drawing on Allen-style interval logic. The engine then uses a Floyd-Warshall transitive closure to resolve implied order.

In plain language: if Alice enters before Bob speaks, and Bob speaks before Carla reacts, the system can infer that Alice enters before Carla reacts. That sounds obvious, but image and video models do not naturally preserve that logic across multiple shots.

Timeline diagram showing before, after, and same-time constraints being resolved into executable multi-actor segments.

Storyboard tools usually encode time weakly. A panel has an order, maybe a duration, and maybe a camera note. But multi-actor timing is richer than panel order:

Timing questionWhy it matters
Does the reaction overlap the action?changes the shot design
Does one actor enter while another is already seated?changes blocking
Does the prop exchange happen before the close-up?affects continuity
Does dialogue begin during movement or after stillness?affects pacing

The GEST-Engine makes timing executable. That is the bar to aim for if we want AI storyboards to become reliable previsualization documents rather than attractive stills.

The LLM Director is constrained by tools

The paper includes an agentic text-to-GEST system. An LLM Director plans a story, but it does not directly mutate the graph. It uses tool calls against a programmatic state backend. The backend validates changes, tracks actors and events, checks capability constraints, and assembles an executable GEST.

That design is important. It avoids the common failure mode where an LLM writes a beautiful but impossible script.

The paper reports that earlier prompt-and-parse pipelines struggled with duplicated actors, dangling references, impossible actions, temporal cycles, and context overflow from the large capability registry. The tool-based Director is the correction: let the LLM decide intent, but let code own state.

That maps directly to Story2Board:

LLM should ownCode should own
story intententity identity
dramatic emphasisprop possession
shot purposetemporal ordering
camera suggestionschema validity
scene rewritecontinuity constraints

This is also why the paper connects naturally to our MAGNET article. Characters can have goals and intentions, but the system still needs a durable world state beneath them.

Labels come free because the world is known

The GEST-Engine exports dense artifacts during a single simulation pass:

ArtifactWhy it matters
RGB videothe visible synthetic scene
Dense depthgeometric supervision
Texture-level instance segmentationobject and surface labels
18-joint skeletal pose per actoractor motion ground truth
Pairwise spatial-relation graphsframe-level relationships between entities
2D bounding boxesdetection and tracking supervision
Event-to-frame mappingsexact alignment between story graph and video
Natural-language descriptionstext paired with executable story state

Diagram of RGB, depth, segmentation, pose, spatial relations, bounding boxes, event-frame mappings, and natural language outputs from one simulation pass.

The phrase "zero marginal annotation cost" is doing real work here. Once the world is executing deterministically, the annotations are not a separate human labeling project. They are a byproduct of the simulation.

For Story2Board, the equivalent is not necessarily segmentation masks. The equivalent is traceability:

Storyboard artifactTraceable back to
panel imageshot record
character appearancecharacter card
prop positionprop state
camera movecamera intent and path
continuity warninggraph comparison
revision historychanged event or constraint

If a generated panel changes a prop, the system should know which graph fact was violated. That is more useful than simply regenerating the image.

The scale is modest but strategically useful

The paper builds on GTA San Andreas through Multi Theft Auto. That choice is pragmatic rather than glamorous. The authors get a mature open world, controllable actors, many animations, low hardware requirements, and parallel execution.

The reported asset capacity is substantial:

ResourceScale
Object models733
Object categories32
Individual animations2,500+
Animation categories101
Actor skins312
Game contexts70+
Currently configured environments11
Implemented granular action types46

The engineering effort is also large. The report describes roughly 38,000 lines of Lua for the engine core, 8,500 lines of C++ for native screenshot and pathfinding pieces, 53,000 lines of Python for generation and the text-to-GEST system, and a small JavaScript visualizer.

This matters because it keeps the paper honest. Explicit world models are not free. They require schemas, validators, capability registries, editors, adapters, capture systems, and batch infrastructure.

The benefit is control.

How it connects to recent world-model papers

The GEST-Engine sits in the same larger direction as World Narrative Model and ABot-3DWorld, but it attacks a different layer.

SystemCore control object
World Narrative Modeleditable physical production state before video rendering
ABot-3DWorld 0spatial primitive and panoramic exploration for reconstructable worlds
GEST-Engineevent graph that deterministically drives multi-actor simulation

WNM is about controlling video through a world blueprint. ABot-3DWorld is about exploring and reconstructing 3D space. GEST-Engine is about making story events executable and observable.

That last part is exactly what storyboard systems need more of. Shot continuity is not only about the same-looking face or the same-looking room. It is also about whether the event logic survived rendering.

What Story2Board should borrow

The best Story2Board version of GEST is not a full simulator. It is an event graph under the storyboard.

Diagram mapping script beats to a Story2Board event graph, Gemini co-director planning, storyboard panels, and validation outputs.

A practical graph could store:

Graph fieldStoryboard use
Actorsidentity, role, current location
Propsownership, visibility, state changes
Locationspersistent set layout and camera constraints
Eventsactions, reactions, dialogue beats
Temporal edgesbefore, after, overlap, same-time
Camera notesshot size, angle, movement, subject priority
Validation flagsimpossible timing, missing prop, inconsistent blocking

This would give Gemini a more reliable substrate. The co-director could still speak naturally, but the system would keep an executable memory of what has to remain true.

That connects to our CANVAS breakdown, where visual continuity is treated as story state, and to our Story2Board consistency article, where pixel-level consistency is only one layer of the problem.

Where the paper is limited

The GEST-Engine is powerful, but its limits are clear.

First, it inherits the look and physics of an old game engine. That is fine for synthetic supervision and diagnostic benchmarks, but it is not final visual quality for modern filmmaking.

Second, manual mapping work matters. The platform may contain 2,500+ animations and 733 objects, but the currently configured subset is smaller. Every new environment, action, and object affordance needs engineering.

Third, camera control exists but is not the center of the paper. For storyboard use, camera language needs to be richer than a spectator workaround. Shot size, lens behavior, camera motivation, eyeline, and coverage logic need first-class treatment.

Fourth, synthetic determinism can hide real-world ambiguity. A real set has messy hands, imperfect blocking, reflections, occlusions, soft cloth, missed marks, and actor improvisation. The graph is a strong contract, not a complete substitute for production judgment.

The product lesson

The GEST-Engine makes a useful argument: the future of AI video planning is not only better pixels. It is better state.

For storyboard tools, that means the central document should not be just images plus captions. It should be a structured graph that knows:

QuestionWhy it matters
Who is in the scene?identity and continuity
What are they doing?action planning
What do they hold?prop state
Where are they?blocking and location memory
What happens first?temporal logic
Which frame proves it?traceable review

That is the bridge from AI image generation to usable previsualization.

The GEST-Engine is a synthetic data system, but the design lesson is broader. A storyboard becomes more useful when every panel can answer: which event created me, which state do I preserve, and which next shot depends on me?

References

Cudlenco, N., Masala, M., & Leordeanu, M. (2026). The GEST-Engine: From Event Graphs to Synthetic Video. arXiv preprint arXiv:2607.12231. https://arxiv.org/abs/2607.12231

Related Posts

Ready to create your storyboard?

Turn your ideas into professional storyboards with Story2Board — the intelligent director assistant.

Try Story2Board Free