Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 50 of the 53 references it cites were found in a registry or an index; 8 of the 15 sources its claims cite were checked for support.

Understanding Creative Potential and Use Cases of AI-Generated Environments for Virtual Film Productions: Insights from Industry Professionals

Open access
Leininger, Pauline, Weber, Christoph Johannes, Rothe, Sylvia · 2025 · Proceedings of the 2025 ACM International Conference on Interactive Media Experiences

Abstract

Virtual production (VP) is transforming filmmaking by integrating real-time digital elements with live-action footage, offering new creative possibilities and streamlined workflows. While industry experts recognize AI’s potential to revolutionize VP, its practical applications and value across different production phases and user groups remain underexplored. Building on initial research into generative and data-driven approaches, this paper presents the first systematic pilot study evaluating three types of AI-generated 3D environments—Depth Mesh, 360° Panoramic Meshes, and Gaussian Splatting—through the participation of 15 filmmaking professionals from diverse roles. Unlike commonly used 2D AI-generated visuals, our approach introduces navigable 3D environments that offer greater control and flexibility, aligning more closely with established VP workflows. Through expert interviews and literature research, we developed evaluation criteria to assess their usefulness beyond concept development, extending to previsualization, scene exploration, and interdisciplinary collaboration. Our findings indicate that different environments cater to distinct production needs, from early ideation to detailed visualization. Gaussian Splatting proved effective for high-fidelity previsualization, while 360° Panoramic Meshes excelled in rapid concept ideation. Despite their promise, challenges such as limited interactivity and customization highlight areas for improvement. Our prototype, EnVis…

Overview

CoChat Summary

TL;DR

This pilot study evaluates three AI-generated 3D environment types—Depth Mesh, 360° Panoramic Meshes (Blockade 3D), and Gaussian Splatting—for virtual film production workflows using the EnVisualAIzer prototype and feedback from 15 filmmaking professionals. Gaussian Splatting was rated best for high-fidelity previsualization, while 360° Panoramic Meshes were most useful for rapid concept ideation, though limited interactivity and customization remain barriers.

Key findings

  • Gaussian Splatting was the highest-rated environment, especially indoors: parallax effect \(M = 3.80\), usable area \(M = 3.47\), visual aesthetics \(M = 3.20\); for creative impact, achieving vision \(M = 3.40\) and fostering creativity \(M = 3.53\), with previsualization, storyboarding, and concept development scores often exceeding 4.0.
  • Blockade 3D performed best outdoors for sparking creativity (\(M = 3.07\)) and moodboards/concept development (\(M = 3.60\)), but lagged in visual quality, realism, and navigability.
  • Depth Mesh received the lowest ratings overall, including outdoor visual quality \(M = 2.67\), but was somewhat useful for moodboards/concept development indoors (\(M = 3.07\)) and for early-stage scene setup.
  • Participants consistently highlighted limited interactivity, customization, navigation, and object placement as key improvement areas across environments.

Methods

  • Preliminary user-centered design included 30–60 minute semi-structured interviews with five film professionals (VFX supervisor, post-production supervisor, cinematographer, VP technician, NeRF expert) to derive requirements.
  • The exploratory evaluation was a controlled lab experiment with 15 filmmakers from diverse roles and experience levels (age 21–48), each session lasting 90–120 minutes.
  • Participants explored six AI-generated environments—three types (Depth Mesh, Blockade Labs 360° HDRI to 3D Mesh, Gaussian Splatting) in indoor and outdoor settings—in randomized order, completed Likert-scale questionnaires, provided think-aloud feedback, and participated in informal interviews analyzed via thematic analysis in MaxQDA.

Limitations

  • The paper states the study is exploratory with a small, diverse sample (\(n=15\)), so results are not broadly generalizable and should be viewed as a foundational step.
  • The paper identifies ambiguity in rating usefulness across production stages, possible selection bias from provider-specific environments, indoor/outdoor rating discrepancies, and probable interdependence between environment characteristics and creative impact.
  • The paper notes it does not address ethical considerations such as authenticity, cultural representation, or broader societal implications; the text also makes evident prototype usability issues, limited visual quality in Depth Mesh and Blockade 3D, and difficulty engaging production designers during initial exploration.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1145/3706370.3727853

Cites

50 of 53 references verified3 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

5 Valid · 1 Not valid · 4 Not checked · 47 Own results and interpretations

19 more claims

Create a free account to see all 57 claims and to verify the 3 references still open.

See all claims — free account
  • Probably not a substantial claim. 24
  • It may state two separate claims as one. 17

Create a free account to see these claims.

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

2 of 2

Citations

Cites

Research works printed but not linked: 7

  1. 10.5555/3666122.3667856 · doi:10.5555/3666122.3667856
  2. Grand View Research. 2024. Virtual Production Market Size, Share & Trends Analysis Report By Component (Software, Hardware, Services), By Type, By End-use, By Region, And Segment Forecasts, 2024 - 2030. Grand View Research. https://www.grandviewresearch.com/industry-analysis/virtual-production-market Online Article. Available: https://www.grandviewresearch.com/industry-analysis/virtual-production-market. Accessed: January 18, 2025.
  3. 10.1007/978-3-322-80058-919 · doi:10.1007/978-3-322-80058-919
  4. Trevor Hogg. 2021. PERSPECTIVES: CHASING THE EVOLVING INDUSTRY NORM FOR VIRTUAL PRODUCTION. VFX Voice Magazine. https://www.vfxvoice.com/perspectives-chasing-the-evolving-industry-norm-for-virtual-production/ Online Article. Available: https://www.vfxvoice.com/perspectives-chasing-the-evolving-industry-norm-for-virtual-production/. Accessed: January 16, 2025.
  5. Noah Kadner. 2019. The Virtual Production Field Guide Volume 1. Unreal Engine. Unreal Engine Website. Available: https://cdn2.unrealengine.com/vp-field-guide-v1-3-01-f0bce45b6319.pdf. Accessed: January 18, 2025.
  6. 10.1007/978-3-540-89350-96 · doi:10.1007/978-3-540-89350-96
  7. 10.1007/978-3-030-58452-824 · doi:10.1007/978-3-030-58452-824

Cited by

See all 3

Metadata

Authors
Leininger, P., Weber, C. J., & Rothe, S.
Affiliations
University of Television and Film Munich (DE)
Venue
Proceedings of the 2025 ACM International Conference on Interactive Media Experiences
Publisher
ACM
Published
2025-05-31
Pages
60-78
OpenAlex
W4410919151
Cited by
3
References
34
Citations by year
2026: 2 · 2025: 1
FWCI
3.55
Type
conference paper
Language
en
Open access
Locations
ACM International Conference on Interactive Media Experiences (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Digital Media and Visual Art
  • Physical Sciences › Computer Science › Computer Graphics and Computer-Aided Design › Computer Graphics and Visualization Techniques
  • Social Sciences › Arts and Humanities › Visual Arts and Performing Arts › Art, Technology, and Culture
Keywords
previsualization, AI-generated images, film production workflow, industry professionals, creative potential

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-12, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-12 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.