Collective Recourse for Generative Urban Visualizations
This work addresses the need for group-level harm mitigation in generative urban visualizations, offering a practical pipeline for community-driven model improvement.
The paper proposes a collective recourse framework for text-to-image diffusion models used in urban visualization, enabling communities to submit structured 'visual bug reports' that trigger model or workflow fixes. Evaluation of 240 synthetic reports shows prompt-level fixes are fastest (median 2.1-3.4 days) but less durable (21-38% recurrence), while dataset edits and reward tweaks are slower (13.5-21.9 days) yet more durable (12-18% recurrence) with higher planner uptake (30-36%).
Text-to-image diffusion models help visualize urban futures but can amplify group-level harms. We propose collective recourse: structured community "visual bug reports" that trigger fixes to models and planning workflows. We (1) formalize collective recourse and a practical pipeline (report, triage, fix, verify, closure); (2) situate four recourse primitives within the diffusion stack: counter-prompts, negative prompts, dataset edits, and reward-model tweaks; (3) define mandate thresholds via a mandate score combining severity, volume saturation, representativeness, and evidence; and (4) evaluate a synthetic program of 240 reports. Prompt-level fixes were fastest (median 2.1-3.4 days) but less durable (21-38% recurrence); dataset edits and reward tweaks were slower (13.5 and 21.9 days) yet more durable (12-18% recurrence) with higher planner uptake (30-36%). A threshold of 0.12 yielded 93% precision and 75% recall; increasing representativeness raised recall to 81% with little precision loss. We discuss integration with participatory governance, risks (e.g., overfitting to vocal groups), and safeguards (dashboards, rotating juries).