BRIDGE: Borderless Reconfiguration for Inclusive and Diverse Gameplay Experience via Embodiment Transformation

TL;DR

BRIDGE, a system that integrates a reconstruction pipeline that detects and tracks players from broadcast video to generate 3D play sequences, with an embodiment-aware visualization framework that decomposes head, trunk, and wheelchair base orientations to represent attention, intent, and mobility, significantly enhanced the perceived naturalness of player postures and made tactical intentions easier to understand.

Abstract

Training resources for parasports are limited, reducing opportunities for athletes and coaches to engage with sport-specific movements and tactical coordination. To address this gap, we developed BRIDGE, a system that integrates a reconstruction pipeline, which detects and tracks players from broadcast video to generate 3D play sequences, with an embodiment-aware visualization framework that decomposes head, trunk, and wheelchair base orientations to represent attention, intent, and mobility. We evaluated BRIDGE in two controlled studies with 20 participants (10 national wheelchair basketball team players and 10 amateur players). The results showed that BRIDGE significantly enhanced the perceived naturalness of player postures and made tactical intentions easier to understand. In addition, it supported functional classification by realistically conveying players' capabilities, which in turn improved participants' sense of self-efficacy. This work advances inclusive sports learning and accessible coaching practices, contributing to more equitable access to tactical resources in parasports.

Figures (6)

• Figure 1: Classification points in wheelchair basketball. IWBF’s formal criteria (red) emphasize trunk mobility in the 1.0–4.5 point system, while players and coaches in our formative study additionally highlighted head mobility and seated body dimensions (blue) as decisive factors.
• Figure 2: System pipeline overview: Input video is processed through player, ball, and court detection, followed by pose estimation and mesh reconstruction. Embodiment mapping and game reconstruction are then integrated to reconstruct the wheelchair basketball scene in a 3D simulation space. Images include still frames from NBA broadcast footage used for research illustration purposes. © NBA / Broadcast rights holders.
• Figure 3: Overview of the embodiment-aware orientation mapping process. Player tracking provides mesh reconstruction, from which head, trunk, and path orientations are referenced. By applying classification-based restrictions, the system generates wheelchair basketball player models. The right panel compares results without mapping and with mapping. Images include a player photograph used for research illustration purposes. © Joshua Gateley / Getty Images.
• Figure 4: The results of User Study 1. (a) Participants rated player movements as more natural in the mapping condition than in the non-mapping condition when watching both Simple and Complex tactical videos. (b) When estimating player points, participants reported that trunk mobility had the greatest influence, followed by body dimensions and head mobility. (c) Participants identified trunk mobility as the most important clue for point estimation.
• Figure 5: The results of User Study 2. (a) Participants reported significantly higher self-efficacy when watching wheelchair-converted videos compared to stand-up basketball videos. (b) For all five subjective measures, both national players and non-elite players gave higher ratings to the converted videos than to the original ones.