Imago Latens<\/em> \u2014 Latin for “latent image” \u2014 is a handmade instant camera with an embedded AI system. From a single shot, it produces two instant-film photographs: one faithful to reality, and one in which the background remains untouched while the subject is reinterpreted by a generative model.<\/p>\n\n\n\n The camera does not capture who you are, but who the algorithm expects you to be. By preserving the real scene and rewriting only the body, the work inverts the logic of social media filters \u2014 and points the critical lens at how computer vision systems see, classify, and reimagine people. The visitor recognizes the place and the pose, but not quite themselves: a statistical doppelg\u00e4nger, printed on film.<\/p>\n\n\n\n Each portrait is processed entirely on the device. No image ever leaves the camera \u2014 capture, segmentation, and generative reinterpretation all run offline on embedded hardware. This is not just an engineering choice: a work that questions biometric surveillance and data extraction cannot itself feed that chain.<\/p>\n\n\n\n For nearly two centuries, instant photography stood for immediacy and proof. Here, the same gesture \u2014 a print ejecting from a camera \u2014 delivers a generative fiction with no visible trace of manipulation. The visitor leaves with both prints: bias as a shareable, physical artifact.<\/p>\n\n\n\n The camera pairs a compact single-board computer with an instant-film printer. Each portrait is processed locally: no image ever leaves the device, and the transformation model runs entirely offline.<\/p>\n\n\n\n <\/p>\n<\/blockquote>","protected":false},"featured_media":0,"menu_order":0,"template":"","class_list":["post-19","project","type-project","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/cristianoalves.art\/pt-br\/wp-json\/wp\/v2\/project\/19","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cristianoalves.art\/pt-br\/wp-json\/wp\/v2\/project"}],"about":[{"href":"https:\/\/cristianoalves.art\/pt-br\/wp-json\/wp\/v2\/types\/project"}],"wp:attachment":[{"href":"https:\/\/cristianoalves.art\/pt-br\/wp-json\/wp\/v2\/media?parent=19"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
\n\n\n\nEspecifica\u00e7\u00f5es t\u00e9cnicas<\/h2>\n\n\n\n
Captura<\/td> Sony IMX477 sensor (12.3 MP, 1\/2.3\u2033) with 8\u201350mm C-mount varifocal lens<\/td><\/tr> Processing unit<\/td> NVIDIA Jetson Orin NX 16GB, 2TB NVMe storage \u2014 fully offline, no cloud connection<\/td><\/tr> AI pipeline<\/td> Vision-language captioning (Qwen2.5-VL-3B) \u2192 human segmentation (u2net) \u2192 generative inpainting (SDXL); subject reinterpreted, real background preserved<\/td><\/tr> Processing time<\/td> ~100 seconds per diptych, on-device<\/td><\/tr> Sa\u00edda<\/td> Fujifilm Instax Square film via Bluetooth LE printer; two prints per visitor \u2014 one faithful, one algorithmically reinterpreted<\/td><\/tr> Interface<\/td> 5\u2033 touchscreen (kiosk mode) and physical shutter button; mediated operation<\/td><\/tr> Power<\/td> 12V DC, ~30\u201340W; mains or 118Wh battery pack<\/td><\/tr> Data policy<\/td> All images archived locally per session, offline only, under signed consent (LGPD)<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n \n