{"paper":{"title":"InstancePin: Instance-Addressable Layout-to-Image Diffusion via Coordinate Pinning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chaoyue Wu, Si Wu, Yunfei Zhang","submitted_at":"2026-08-01T10:54:24Z","abstract_excerpt":"Layout-to-image diffusion models have achieved impressive semantic controllability by conditioning generation on category-level segmentation maps. However, such category-aligned control is not necessarily instance-addressable: multiple nearby objects from the same category are often treated as a shared semantic region, leading to ambiguous boundaries, averaged appearances, and feature confusion among instances. This limitation is particularly evident in urban scene synthesis, where small and crowded pedestrians or vehicles require fine-grained instance separation while preserving global scene "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00588","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2608.00588/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}