GroundLink: Exploring How Contextual Meeting Snippets Can Close Common Ground Gaps in Editing 3D Scenes for Virtual Production

TL;DR

GroundLink presents a Unity add-on that embeds meeting-derived decisions and rationale into the 3D editing workflow to close common ground gaps in virtual production. By coupling a Meeting Knowledge Dashboard with in-situ constraint-aware feedforward and bidirectional synchronization, GroundLink enables faster onboarding, clearer intent, and higher perceived editing confidence for distributed VP teams. The authors validate their approach through a formative study, a comparative within-subjects study, and expert evaluations, reporting improved perceived common ground and workflow potential despite concerns about visual clutter and overreliance. The work contributes a concrete design and empirical insights for integrating meeting-derived knowledge into production tools, with implications for other remote collaboration and 3D content creation domains.

Abstract

Virtual Production (VP) professionals often face challenges accessing tacit knowledge and creative intent, which are important in forming common ground with collaborators and in contributing more effectively and efficiently to the team. From our formative study (N=23) with a follow-up interview (N=6), we identified the significance and prevalence of this challenge. To help professionals access knowledge, we present GroundLink, a Unity add-on that surfaces meeting-derived knowledge directly in the editor to support establishing common ground. It features a meeting knowledge dashboard for capturing and reviewing decisions and comments, constraint-aware feedforward that proactively informs the editor environment, and cross-modal synchronization that provides referential links between the dashboard and the editor. A comparative study (N=12) suggested that GroundLink help users build common ground with their team while improving perceived confidence and ease of editing the 3D scene. An expert evaluation with VP professionals (N=5) indicated strong potential for GroundLink in real-world workflows.

Figures (6)

• Figure 1: Formative study results on collaboration practices for virtual production. (A) shows frequency of collaboration for cross- vs. single-functional collaboration. (B) shows the challenges in current collaboration practices (multiple responses possible). (C) shows the tools that professionals currently use for collaboration (multiple responses possible).
• Figure 2: Formative study results on onboarding practices in virtual production. (A) shows the frequency of the onboarding activities, (B) shows the methods that collaborators use (multiple responses possible - each is out of 15/23 who reported their onboarding experiences.), and (C) shows the self-reported difficulty levels of onboarding, from the perspectives of onboarding others and being onboarded to a scene.
• Figure 3: To illistrate how GroundLink supports common ground formation, consider Bob, a VFX artist newly assigned to a river scene. Traditionally, Alice (the production supervisor) would onboard him through meetings and explanations of past decisions. With GroundLink, Bob instead uncovers the scene's collaborative history while working. (A) Moment 1: Resolving Ambiguous References. Bob is tasked with moving the sub camera. With GroundLink, clicking the object in the dashboard highlights the specific camera in the 3D editor, eliminating the need for second guessing. (B) Moment 2: Revealing Implicit Constraints. Bob's task is to move the boat upstream, but he does not know a no-placement zone was established two meetings ago. With GroundLink, past decisions and a feedforward cue appear as subtle red zones in the editor, expanding and darkening as the boat nears. This helps Bob avoid placing the boat in the restricted area. (C) Moment 3: Context-Rich, Targeted Queries. Bob is tasked with adjusting the light to create a dappled light effect, a term he does not know or understand in this scene. With GroundLink, he can ask the AI summary a targeted question about the scene and object of interest, avoiding unnecessary second guessing.
• Figure 4: GroundLink summarizes verbal information in a sequential representation on a dashboard. (A) The minimap displays all element changes on a zoomable map. (B) Users can filter decision/comment entries by collaborator, object, meeting phase, meeting, and date range. (C) The summary view lists all changes/comments. (D) For each entry, contributor badges and agreements are attached. (E) The video player with timeline (synchronized with other panels) and meeting list allows users to watch video while reviewing decisions/comments. (F) The AI summary and chat enables quick glances and Q&A.
• Figure 5: GroundLink surfaces in-situ feedforward derived from meeting recordings: (A) encouragement zone, (B) restriction zone, (C) department icons, (D) inspector feedforward for styling compliance.