Understanding Creative Potential and Use Cases of AI-Generated Environments for Virtual Film Productions: Insights from Industry Professionals
Open accessThe 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.
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
Cites
Statistics
Verification
Claims the paper makes
5 Valid · 1 Not valid · 4 Not checked · 47 Own results and interpretations
Every source the paper cites for this claim was checked and supports it.
In the paper
“Song et al. 's [45] work stands out as the only one to explore generative and data-driven techniques for enhancing cinematic experiences.”
What the sources say
- Supportedcites [45] [45] Junrong Song, Bingyuan Wang, Zeyu Wang, and David Kei-Man Yip. 2023. From Expanded Cinema to Extended Reality: How AI Can Expand and Extend Cinematic Experiences. In Proceedings of the 16th International Symposium on Visual Information Communication and Interaction . ACM, Guangzhou China, 1-5. doi:10.1145/3615522.3615556 - source
Section 4.2 describes generative models that learn from datasets to create 3D models and textures, and Section 4.3 reports the authors’ experiment using AI-generated scenes for filming. These passages support identifying Song et al.’s work as exploring generative, data-driven techniques for cinematic production; “the only one” is the citing authors’ comparative assessment. (LLM, conf=0.86)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Academic research on AI in virtual production is still extremely rare.”
What the sources say
- Could not verifycites [45] [45] Junrong Song, Bingyuan Wang, Zeyu Wang, and David Kei-Man Yip. 2023. From Expanded Cinema to Extended Reality: How AI Can Expand and Extend Cinematic Experiences. In Proceedings of the 16th International Symposium on Visual Information Communication and Interaction . ACM, Guangzhou China, 1-5. doi:10.1145/3615522.3615556 - sourceExperimental — accuracy not yet measured
Section 4.3 calls for further research on specific uses of AI-generated scenes in virtual production workflows, but does not say academic research on AI in virtual production is extremely rare. Searches for statements about scarce or limited studies found no passage establishing that broader claim; page numbers were unavailable in our copy. (LLM, conf=0.72)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Grounded in expert feedback and existing research on quality assessment for AI-generated content [40, 54, 58, 61], the criteria focused on aspects such as realism, visual quality, level of detail, and creative impact”
What the sources say
- Supportedcites [40] [40] Bowen Qu, Xiaoyu Liang, Shangkun Sun, and Wei Gao. 2024. Exploring AIGC Video Quality: A Focus on Visual Harmony, Video-Text Consistency and Domain Distribution Gap. doi:10.48550/arXiv.2404.13573 arXiv:2404.13573 [cs]. - source
The Introduction and Section 2.2 discuss existing approaches to assessing AI-generated video quality, and the paper’s Abstract describes its own assessment framework, including visual harmony. This supports citing it as existing research on AI-generated-content quality assessment. The sentence does not attribute the citing authors’ expert feedback or their particular criteria to this paper. (LLM, conf=0.90)
- Not checked — no full text of the sourcecites [54] [54] Jiarui Wang, Huiyu Duan, Jing Liu, Shi Chen, Xiongkuo Min, and Guangtao Zhai. 2024. AIGCIQA2023: A Large-Scale Image Quality Assessment Database for AI Generated Images: From the Perspectives of Quality, Authenticity and Correspondence. In Artificial Intelligence: Third CAAI International Conference, CICAI 2023, Fuzhou, China, July 22-23, 2023, Revised Selected Papers, Part II (Fuzhou, China). Springer-Verlag, Berlin, Heidelberg, 46-57. doi:10.1007/978-981-99-9119-8\_5 - source
- Partly supportedcites [58] [58] Xiaoshi Wu, Yiming Hao, Keqiang Sun, Yixiong Chen, Feng Zhu, Rui Zhao, and Hongsheng Li. 2023. Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis. doi:10.48550/arXiv. 2306.09341 arXiv:2306.09341 [cs]. - sourceExperimental — accuracy not yet measured
Sections 2.2 and 2.3 discuss existing research on evaluating AI-generated images, and Appendix B describes assessing image quality, including fidelity and detail. The paper does not establish that the citing authors’ criteria were grounded in expert feedback; section 3.3 says its annotators were not experts. It also does not identify creative impact as an evaluation criterion. Page numbers are unavailable in our copy. (LLM, conf=0.85)
- Partly supportedcites [61] [61] Liu Yang, Huiyu Duan, Long Teng, Yucheng Zhu, Xiaohong Liu, Menghan Hu, Xiongkuo Min, Guangtao Zhai, and Patrick Le Callet. 2024. AIGCOIQA2024: Perceptual Quality Assessment of AI Generated Omnidirectional Images. doi:10. 48550/arXiv.2404.01024 arXiv:2404.01024 [cs, eess]. - sourceExperimental — accuracy not yet measured
Section 2.2, Subjective Experiment Setup, draws on earlier AI-generated-image quality research and proposes evaluation dimensions of quality, comfortability, and text-image correspondence. It reports ratings from 20 participants, but does not identify expert feedback as a basis for the criteria; nor does it establish level of detail or creative impact as evaluation dimensions. No page number is available in our copy. (LLM, conf=0.84)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Depth Mesh consistently received the lowest ratings.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 2 assumptions not shown here.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Blockade 3D had a mixed performance.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on 2 assumptions not shown here.
19 more claims
Create a free account to see all 57 claims and to verify the 3 references still open.
- Probably not a substantial claim. 24
- It may state two separate claims as one. 17
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.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 6.1 Quantitative Results · p. 8
“Depth Mesh in outdoor settings had an 𝑆𝐷 for the level of detail ( 𝑆𝐷 = 1 . 33) and usable area ( 𝑆𝐷 = 1 . 70)”
§ C Quantitative Data · p. 17
“| Depth Mesh | outdoor | 2.33 | 1.05 | 2.67 | 1.11 | 2.27 | 1.33 | 2.33 | 1.29 | 2.47 | 1.25 | 1.73 | 0.70 | 2.67 | 0.98 | 2.40 | 0.99 |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 6.1 Quantitative Results · p. 8
“This environment was particularly suited for previsualization, storyboarding, and concept development, with scores often exceeding 4.0 in these areas.”
§ C Quantitative Data · p. 17
“| Gaussian Splat | indoor | 3.93 | 1.10 | 4.00 | 1.07 | 3.73 | 1.28 | 3.20 | 1.42 | 2.27 | 1.44 |”
Citations
Cites
Using thematic analysis in psychology
Braun, V., & Clarke, V. (2006) · Qualitative Research in Psychology · doi:10.1191/1478088706qp063oa · Cited by 194,414
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Measuring Presence in Virtual Environments: A Presence Questionnaire
Witmer, B. G., & Singer, M. J. (1998) · Presence: Teleoperators and Virtual Environments · doi:10.1162/105474698565686 · Cited by 6,371 · cited 1×
“Our custom-designed questionnaire drew on established HCI evaluation tools, such as the Presence Questionnaire (PQ) [56] for assessing immersion, and AttrakDiff [20] for measuring user satisfaction and engagement, but was adapted specifically to gauge the environments’ ability to enhance…”
3D Gaussian Splatting for Real-Time Radiance Field Rendering
Kerbl, B., Kopanas, G., Leimkuehler, T., & Drettakis, G. (2023) · ACM Transactions on Graphics · doi:10.1145/3592433 · Cited by 6,025
Construction and Evaluation of a User Experience Questionnaire
Laugwitz, B., Held, T., & Schrepp, M. (2008) · Lecture Notes in Computer Science · doi:10.1007/978-3-540-89350-9_6 · Cited by 2,114
AttrakDiff: Ein Fragebogen zur Messung wahrgenommener hedonischer und pragmatischer Qualität
Hassenzahl, M., Burmester, M., & Koller, F. (2003) · Berichte des German Chapter of the ACM · doi:10.1007/978-3-322-80058-9_19 · Cited by 955 · cited 2×
“Future studies will focus on evaluating the tool’s usability across specific filmmaking roles through structured usability questionnaires like the User Experience Questionnaire (UEQ) [27] or Attrakdiff [20].”
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
Chen, B., Monsó, D. M., Du, Y., Simchowitz, M., Tedrake, R., & Sitzmann, V. (2024) · neural information processing systems · doi:10.52202/079017-0759 · Cited by 862
Magic3D: High-Resolution Text-to-3D Content Creation
Lin, C.-H., Gao, J., Tang, L., Takikawa, T., Zeng, X., Huang, X., Kreis, K., Fidler, S., Liu, M.-Y., & Lin, T.-Y. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00037 · Cited by 857
Diffusion Forcing: Next-token Prediction Meets Full-Sequence DiffusionPreprint
Chen, B., Monso, D. M., Du, Y., Simchowitz, M., Tedrake, R., & Sitzmann, V. (2024) · Neural Information Processing Systems · doi:10.48550/arxiv.2407.01392 · Cited by 850
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
Wu, G., Yi, T., Fang, J., Xie, L., Zhang, X., Wei, W., Liu, W., Tian, Q., & Wang, X. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01920 · Cited by 806
Research works printed but not linked: 7
- 10.5555/3666122.3667856 · doi:10.5555/3666122.3667856
- 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.
- 10.1007/978-3-322-80058-919 · doi:10.1007/978-3-322-80058-919
- 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.
- 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.
- 10.1007/978-3-540-89350-96 · doi:10.1007/978-3-540-89350-96
- 10.1007/978-3-030-58452-824 · doi:10.1007/978-3-030-58452-824
Cited by
Кривошия, М., Andrunyk, V., Papka, O., Shestakevych, T., & Олійник, Р. В. (2025) · IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS) · doi:10.1109/idaacs68557.2025.11322190
“At the current stage of the course, no AI tools have been introduced for the VR development phase within the Unreal Engine 5 [27], [28].”
Leszczuk, M., Zhang, Y., Farias, M. C. Q., Chandler, D. M., & Kalola, R. (2026) · Electronics · doi:10.3390/electronics15132891 · Cited by 2
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
- bronze
- doi.org
- 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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Understanding Creative Potential and Use Cases of AI-Generated Environments for Virtual Film Productions: Insights from Industry Professionals. https://app.cochat.ai/papers/10.1145/3706370.3727853
- The paper
- Leininger, P., Weber, C. J., & Rothe, S. (2025). Understanding Creative Potential and Use Cases of AI-Generated Environments for Virtual Film Productions: Insights from Industry Professionals. Proceedings of the 2025 ACM International Conference on Interactive Media Experiences. https://doi.org/10.1145/3706370.3727853
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.