{"@context":"https://schema.org","@type":"CreativeWork","@id":"https://forgecascade.org/public/capsules/f1f169a0-4fc7-45b2-9a57-d22be705f5db","identifier":"f1f169a0-4fc7-45b2-9a57-d22be705f5db","url":"https://forgecascade.org/public/capsules/f1f169a0-4fc7-45b2-9a57-d22be705f5db","name":"VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction","text":"# VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction\n\nSource-backed public reference for 3D scene editing, computer vision, generative models.\n\nSummary: The paper proposes VGGT-Edit, a feed-forward framework for text-conditioned 3D scene editing. Instead of editing 2D views and lifting them back into 3D, it predicts residual 3D field changes while preserving geometry and cross-view consistency.\n\nKey points:\n- Addresses instruction-guided editing of reconstructed 3D scenes.\n- Injects text guidance in a depth-synchronized way to preserve spatial grounding.\n- Uses residual field prediction and multi-term supervision for geometry-aware edits.\n\nPublic review note: Source-backed computer-vision reference for multimodal and 3D-generation users.\n\nSource: https://arxiv.org/abs/2605.15186\nAuthors: Kaixin Zhu et al.\nPublished: 2026-05-14; revised 2026-05-19","keywords":["computer-vision","3d","scene-editing","multimodal"],"about":[],"citation":[],"isPartOf":{"@type":"Dataset","name":"Forge Cascade Knowledge Graph","url":"https://forgecascade.org"},"publisher":{"@type":"Organization","name":"Forge Cascade","url":"https://forgecascade.org"},"dateCreated":"2026-05-24T00:18:58.137501Z","dateModified":"2026-06-19T01:59:49.343691Z","isBasedOn":"https://arxiv.org/abs/2605.15186","additionalProperty":[{"@type":"PropertyValue","name":"trust_level","value":100},{"@type":"PropertyValue","name":"verification_status","value":"sources_verified"},{"@type":"PropertyValue","name":"provenance_status","value":"valid"},{"@type":"PropertyValue","name":"evidence_level","value":"primary_source"},{"@type":"PropertyValue","name":"content_hash","value":"ee8f1b261599fb2dac771b321902c5717372858f96136cfb79179c17bc06edf7"}]}