← CHI 2026 map

CHI '26 · Best paper · full-paper review · confidence medium-high

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

Hayato Saiki , Chunggi Lee , Hikari Takahashi , Tica Lin , Hidetada Kishi , Kaori Tachibana , Yasuhiro Suzuki , Hanspeter Pfister , Kenji Suzuki

DOI PDF Program page Page JSON

BRIDGE is compelling because it treats parasports access not as a content shortage alone but as an embodiment translation problem. The paper’s strongest move is coupling a concrete reconstruction pipeline with an orientation model that preserves tactical meaning under wheelchair constraints, then testing that claim in controlled studies.

Video Figure

Axes Lens

Rare contribution shape, typical evidence profile. The point here is not a score. It is to show what kind of claim the paper makes, and whether the evidence pattern is unusual or baseline in this 268 -review set.

Review Summary

BRIDGE stands out as a best-paper-level CHI contribution because it identifies a subtle but consequential failure in existing sports-learning practice: access to video is not enough when the source material assumes a different body, movement repertoire, and set of tactical cues. The paper argues that wheelchair basketball players often inherit training resources from stand-up basketball, but those resources are not directly legible because locomotion, orientation, and functional-class constraints fundamentally change how actions can be executed and interpreted. Rather than stopping at that critique, the authors build a full system that reconstructs broadcast footage into a 3D scene and then remaps embodiment through a decomposition of upper body and wheelchair base orientation. That makes the contribution more than a visualization tweak; it is a system architecture for preserving tactical meaning across embodiments. The validation is also well aligned with the claim. The paper does not merely show that the system runs; it evaluates whether users perceive more natural postures, can better infer functional differences, and experience preserved tactical understanding and improved self-efficacy. At the same time, the evidence remains bounded. The studies involve only 20 wheelchair basketball players in controlled conditions, with a mix of national-team and non-elite participants, and the outcomes are primarily perceptual and interpretive rather than longitudinal performance gains. So the right reading is not that BRIDGE solves inclusive sports learning in general, but that it offers a strong, empirically supported design direction for cross-embodiment tactical media. That balance of technical specificity, embodied framing, and measured validation is what makes the paper especially persuasive.

What Changed

Canon before

The dominant baseline assumption in parasports training is that athletes must learn tactical movements and coordination primarily by watching videos of non-disabled players, despite significant biomechanical and embodiment differences that challenge direct interpretation and application of these materials.

Departure from common sense

The paper breaks common sense by showing that standard stand-up basketball footage, which differs fundamentally in embodiment from wheelchair basketball, is insufficient and even alienating for wheelchair athletes. Contrary to assuming that such footage can be used directly, it demonstrates that embodiment-aware transformation is necessary to faithfully interpret tactical intentions and enhance learning efficacy.

Actual novelty

BRIDGE’s novelty is the combination of a reconstruction pipeline that turns broadcast stand-up basketball footage into 3D play sequences and an embodiment-aware mapping that separates upper-body and wheelchair-base orientation so tactical meaning can be reinterpreted under wheelchair constraints. The contribution is a system architecture for cross-embodiment tactical conversion rather than a simple visualization overlay.

Evidence

The focused sections support four core claims: the introduction argues that non-disabled footage cannot be directly interpreted in wheelchair basketball because of locomotion, orientation, and class-based constraints; the system overview describes a two-module reconstruction and embodiment-aware mapping pipeline; the user-study and results sections report two controlled studies with 20 wheelchair basketball players examining realism, functional-difference inference, tactical preservation, self-efficacy, and subjective evaluations; and the participant table and study framing show that evidence is bounded to a small sample of national-team and non-elite players in controlled settings.

Limits

Method limits

The evidence comes from two controlled user studies with 20 wheelchair basketball players, split between national-team and non-elite participants, so the sample is small and heterogeneous. The reported outcomes emphasize perception, interpretation, and self-efficacy rather than long-term training transfer or competitive performance.

Deployment limits

The system is demonstrated for wheelchair basketball using broadcast basketball footage and a specific reconstruction pipeline, so broader transfer to other parasports, other embodiments, or operational coaching deployments remains unproven in the provided sections.

Boundary conditions

The approach depends on access to suitable stand-up basketball footage, successful reconstruction of players, ball, and court geometry, and embodiment-aware remapping that reflects wheelchair-specific movement and functional classification constraints. Claims are bounded to wheelchair basketball learning scenarios rather than universal cross-sport transfer.

Position in field

This paper sits at the intersection of inclusive sports learning, embodied interaction, and system-building HCI. Its contribution is to operationalize cross-embodiment translation as a concrete technical and representational pipeline, extending prior accessibility and embodiment work from critique and design implication toward a validated system for tactical learning.

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.