{"observation":{"id":"029b8c65-f8b1-4fcb-9b41-609b00c5f50d","tool":"media-io","tool_name":"Media.io","criterion":"motion-handling","criterion_name":"Motion handling","criterion_definition":"Does quality degrade when the subject moves quickly, gestures, or leans?","criterion_evidence_type":"transformation","criterion_rank_role":"decisive","criterion_rank_role_reason":"A video-background tool has to keep working when the subject moves; failure here means the core effect breaks down. (3 of 3 judges)","scenario":"busy-urban-street","scenario_name":"Busy Urban Street","group_tag":"remove-or-replace-video-backgrounds-using-ai","scenario_description":"A video of a person walking through a busy city street with multiple people, moving vehicles, and a visually complex urban background. It was used to stress segmentation and tracking under heavy background distraction and continuous motion.","modality":"video","input_text":null,"input_artifact_refs":[{"alt":null,"url":"https://d3epheqghktydj.cloudfront.net/remove-or-replace-video-backgrounds-usin-input-3-8dd8c54c98be.mp4","role":"input","filename":"Input 3.mp4"}],"stresses":["Complex background segmentation","Handling background distractions","Subject tracking","Temporal consistency across frames","Edge accuracy during continuous movement"],"verdict":"worked","score":null,"score_total":null,"note":"The cutout held up as several people shifted position through the frame, including one person moving from center toward the right and others entering at the edges.","evidence_state":"verified","source":null,"artifacts":[{"url":"https://cdn.futuresmart.ai/public/aidemos/0122df81cac54b59ab38e07ee86290c2.mp4?v=1","role":"input","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/4cc8b5b6c5ea473bb202bb1be577a550.mp4?v=1","role":"output","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/e8576ad6fc8943d484a17a423a087947.mp4?v=1","role":"output","alt":null},{"url":"https://cdn.futuresmart.ai/public/aidemos/f71888caf9ee4f479093d8d5108f9909.mp4?v=1","role":"output","alt":null}],"run_id":"10155228-7ce8-438a-a210-547331ef080b","study_title":"Remove or Replace Video Backgrounds Using AI","study_kind":"generation","research_task":"86ba42c2d","tested_at":null,"completeness":"input-and-output","input":{"state":"files","text":null,"files":[{"url":"https://d3epheqghktydj.cloudfront.net/remove-or-replace-video-backgrounds-usin-input-3-8dd8c54c98be.mp4","filename":"Input 3.mp4","alt":"Busy Urban Street","role":"input"}],"modality":"video","stresses":["Complex background segmentation","Handling background distractions","Subject tracking","Temporal consistency across frames","Edge accuracy during continuous movement"]},"tool_page_slug":"media-io","tool_url":"https://aidemos.com/tools/media-io","permalink":"https://aidemos.com/evidence/029b8c65-f8b1-4fcb-9b41-609b00c5f50d","api_url":"https://ai.aidemos.com/v1/observations/029b8c65-f8b1-4fcb-9b41-609b00c5f50d"},"peers":[{"id":"3fdb7ce8-2f77-457f-83c9-ae067f7d42d6","tool":"bria-ai","tool_name":"Bria.ai","verdict":"worked","score":null,"score_total":null,"note":"Both pedestrians remained separately isolated while walking, so multi-subject motion did not cause subject loss.","artifact_count":4,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/1778c904fac34eb5a5ff16bb86c923f3.mp4?v=1","evidence_url":"https://aidemos.com/evidence/3fdb7ce8-2f77-457f-83c9-ae067f7d42d6"},{"id":"34a2cdbc-b9d3-4de7-9da0-109ebb7e07fd","tool":"cutout-pro","tool_name":"Cutout.Pro","verdict":"worked","score":null,"score_total":null,"note":"Keeps a moving foreground pedestrian isolated while the background stays removed, and even a second person can appear as a separate cutout in one frame.","artifact_count":3,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/20b5f3786a08406283ec8b5aab4ab63e.webm?v=1","evidence_url":"https://aidemos.com/evidence/34a2cdbc-b9d3-4de7-9da0-109ebb7e07fd"},{"id":"e3c61c02-05e0-4f16-900a-2d0a34620c06","tool":"descript","tool_name":"Descript","verdict":"struggled","score":null,"score_total":null,"note":"The requested in-motion subjects are rendered more static and posed than the source’s forward-stride feel, so motion energy is flattened.","artifact_count":1,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/2643dedbeb40423fa5999d7469a0f416.png?v=1","evidence_url":"https://aidemos.com/evidence/e3c61c02-05e0-4f16-900a-2d0a34620c06"},{"id":"8e59fc53-0d63-4ab8-98f2-55c7f4a84354","tool":"fotor","tool_name":"Fotor","verdict":"worked","score":null,"score_total":null,"note":"The tool tracked 3–4 background pedestrians at once through a full 20-second continuous-motion clip without merging or dropping anyone.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/d27ac7ac52bd48e4be9f37de63fe5b5b.mp4?v=1","evidence_url":"https://aidemos.com/evidence/8e59fc53-0d63-4ab8-98f2-55c7f4a84354"},{"id":"5f180402-d5a5-4872-adad-33942d1ff44d","tool":"invideo-ai","tool_name":"InVideo AI","verdict":"worked","score":null,"score_total":null,"note":"It kept the subject and secondary pedestrians consistent through a full ~20-second continuous walking shot, with no ghosting or motion breakdown.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/2a8f5912d1244f47b145c185e08cba33.mp4?v=1","evidence_url":"https://aidemos.com/evidence/5f180402-d5a5-4872-adad-33942d1ff44d"},{"id":"9e6ab621-70d9-44c8-bb66-97dfd8502194","tool":"kapwing","tool_name":"Kapwing","verdict":"struggled","score":null,"score_total":null,"note":"At several other points in the busy-street clip, incompletely erased gray blobs and leftover pedestrian traces lingered on the white background instead of being fully removed.","artifact_count":2,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/1585b475786d48cebd13908b7c705519.png?v=1","evidence_url":"https://aidemos.com/evidence/9e6ab621-70d9-44c8-bb66-97dfd8502194"},{"id":"a7e199a2-b296-416a-aed7-56347e28116f","tool":"picsart","tool_name":"Picsart","verdict":"failed","score":null,"score_total":null,"note":"In a two-person moving street clip, the primary walker stayed isolated but the second pedestrian was erased entirely, indicating a single-subject lock-on in dynamic scenes.","artifact_count":5,"thumbnail":"https://cdn.futuresmart.ai/public/aidemos/58fe281c360d406e9526f2d65f26306e.png?v=1","evidence_url":"https://aidemos.com/evidence/a7e199a2-b296-416a-aed7-56347e28116f"}],"other_criteria":[{"id":"5d9722ee-5bad-4816-b6b6-0ba863ed2a50","criterion":"edge-quality","criterion_name":"Edge quality","rank_role":"decisive","verdict":"struggled","score":null,"score_total":null,"note":"For moving multi-person footage, jacket, sleeve, and pant-leg boundaries faded gradually into black instead of cutting sharply, leaving a soft feathered outline.","artifact_count":6,"evidence_url":"https://aidemos.com/evidence/5d9722ee-5bad-4816-b6b6-0ba863ed2a50"},{"id":"04f7a761-7012-4add-9893-5c332879dc65","criterion":"hair-and-fine-detail","criterion_name":"Hair and fine detail","rank_role":"decisive","verdict":"struggled","score":null,"score_total":null,"note":"The fuzzy fur trim on the hood lost individual-strand texture and became a soft blurred blob against black.","artifact_count":5,"evidence_url":"https://aidemos.com/evidence/04f7a761-7012-4add-9893-5c332879dc65"},{"id":"d69e913b-6a51-4699-ab80-dc8a91fb4e9a","criterion":"lighting-adaptation","criterion_name":"Lighting adaptation","rank_role":"decisive","verdict":"struggled","score":null,"score_total":null,"note":"A solid-black cutout result still left subjects floating with zero ground contact and no shadow, so the composite reads as pasted in rather than naturally lit.","artifact_count":5,"evidence_url":"https://aidemos.com/evidence/d69e913b-6a51-4699-ab80-dc8a91fb4e9a"}],"appears_in":[{"page_type":"ranking","slug":"video-background-removers","title":"Best AI Tools to Remove or Replace Video Backgrounds with AI","url":"https://aidemos.com/best/video-background-removers","binding":"run"}],"same_scenario":[{"id":"3fdb7ce8-2f77-457f-83c9-ae067f7d42d6","tool":"bria-ai","tool_name":"Bria.ai","verdict":"worked","score":null,"score_total":null,"note":"Both pedestrians remained separately isolated while walking, so multi-subject motion did not cause subject loss."},{"id":"34a2cdbc-b9d3-4de7-9da0-109ebb7e07fd","tool":"cutout-pro","tool_name":"Cutout.Pro","verdict":"worked","score":null,"score_total":null,"note":"Keeps a moving foreground pedestrian isolated while the background stays removed, and even a second person can appear as a separate cutout in one frame."},{"id":"e3c61c02-05e0-4f16-900a-2d0a34620c06","tool":"descript","tool_name":"Descript","verdict":"struggled","score":null,"score_total":null,"note":"The requested in-motion subjects are rendered more static and posed than the source’s forward-stride feel, so motion energy is flattened."},{"id":"8e59fc53-0d63-4ab8-98f2-55c7f4a84354","tool":"fotor","tool_name":"Fotor","verdict":"worked","score":null,"score_total":null,"note":"The tool tracked 3–4 background pedestrians at once through a full 20-second continuous-motion clip without merging or dropping anyone."},{"id":"5f180402-d5a5-4872-adad-33942d1ff44d","tool":"invideo-ai","tool_name":"InVideo AI","verdict":"worked","score":null,"score_total":null,"note":"It kept the subject and secondary pedestrians consistent through a full ~20-second continuous walking shot, with no ghosting or motion breakdown."},{"id":"9e6ab621-70d9-44c8-bb66-97dfd8502194","tool":"kapwing","tool_name":"Kapwing","verdict":"struggled","score":null,"score_total":null,"note":"At several other points in the busy-street clip, incompletely erased gray blobs and leftover pedestrian traces lingered on the white background instead of being fully removed."},{"id":"a7e199a2-b296-416a-aed7-56347e28116f","tool":"picsart","tool_name":"Picsart","verdict":"failed","score":null,"score_total":null,"note":"In a two-person moving street clip, the primary walker stayed isolated but the second pedestrian was erased entirely, indicating a single-subject lock-on in dynamic scenes."}]}