segment-anything

[ICLR 2025, Oral] EmbodiedSAM: Online Segment Any 3D Thing in Real Time

Keras beit, caformer, CMT, CoAtNet, convnext, davit, dino, efficientdet, edgenext, efficientformer, efficientnet, eva, fasternet, fastervit, fastvit, flexivit, gcvit, ghostnet, gpvit, hornet, hiera, iformer, inceptionnext, lcnet, levit, maxvit, mobilevit, moganet, nat, nfnets, pvt, swin, tinynet, tinyvit, uniformer, volo, vanillanet, yolor, yolov7, yolov8, yolox, gpt2, llama2, alias kecam

[Proyek Open-Source] Menggabungkan MMOCR dengan Segment Anything & Stable Diffusion. Secara otomatis mendeteksi, mengenali, dan melakukan segmentasi instance teks, dengan beberapa tugas downstream, misal: Penghapusan Teks dan Inpainting Teks.

[AAAI 2025] Implementasi resmi PyTorch untuk "TinySAM: Pushing the Envelope for Efficient Segment Anything Model"

Kode resmi untuk "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"