└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Awesome-segment-anything-extensions [![Awesome](https://awesome.re/badge.svg)](https://awesome.re) [![Awesome Anything](https://img.shields.io/badge/Awesome-Anything-blue)](https://github.com/topics/awesome) 2 | 3 | 4 | Segment-anything related awesome extensions/projects/repos/applications. 5 | 6 | Welcome to starts ⭐ & comments 💹 & sharing 😀 !! 7 | 8 | ```diff 9 | - 2023.4.9: Recent works/projects (from 2023) 10 | - welcome to add if any information misses. 😎 11 | ``` 12 | 13 | --- 14 | 15 | 16 | ## Recent Works 17 | - Segment Anything Model (SAM) official [Repo](https://github.com/facebookresearch/segment-anything) 18 | 19 | The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model. 20 | 21 | ![image](https://user-images.githubusercontent.com/65257938/230819542-5e82c99a-1c5b-43a2-9118-e79cfd2b377f.png) 22 | 23 | - Grounded-Segment-Anything (Combination of Ground-DINO and Segment-Anything) [Repo](https://github.com/IDEA-Research/Grounded-Segment-Anything#grounded-segment-anything) 24 | 25 | ![image](https://user-images.githubusercontent.com/65257938/230819682-b2987eb9-24dd-467b-b7e2-203236f4c969.png) 26 | 27 | - Segment-Any-Anomaly + (SAM + hybrid prompt regularization for zero-shot anomaly detection)[ArXiV](https://arxiv.org/abs/2305.10724) 28 | 29 | ![image](https://github.com/JerryX1110/awesome-segment-anything-extensions/assets/65257938/88ef3796-ebe3-44e6-9697-0c37d463f769) 30 | 31 | ![image](https://github.com/JerryX1110/awesome-segment-anything-extensions/assets/65257938/320a7fb4-cb2b-447c-8013-b4a4610b0b02) 32 | 33 | - Segment Any Point Cloud Sequences (SAM for self-supervised learning on large-scale 3D point clouds) [Repo](https://github.com/youquanl/Segment-Any-Point-Cloud) [ArXiv](https://arxiv.org/abs/2306.09347) [Page](https://ldkong.com/Seal) 34 | 35 | ![image](https://github.com/JerryX1110/awesome-segment-anything-extensions/assets/65257938/01b9f025-7a40-4b37-ba60-45e90f27c68f) 36 | 37 | 38 | 39 | - Segment-Any-Anomaly (SAM + GroudingDINO for anomaly detection)[Repo](https://github.com/caoyunkang/Segment-Any-Anomaly) 40 | 41 | ![image](https://user-images.githubusercontent.com/65257938/230824120-4efa057e-6a0f-41d5-b995-768496d1edcc.png) 42 | 43 | 44 | - Segment and Track Anything (SAM-Track) [Repo](https://github.com/z-x-yang/Segment-and-Track-Anything) [ArXiv](https://arxiv.org/abs/2305.06558) 45 | 46 | ![image](https://user-images.githubusercontent.com/65257938/232959211-6ee84ad5-a02d-44ca-91d2-17d12b978fb2.png) 47 | 48 | - Inpaint/Remove/Fill-Anything (image inpainting meets sam) [Repo](https://github.com/geekyutao/Inpaint-Anything) 49 | 50 | ![image](https://user-images.githubusercontent.com/65257938/233364976-ce36b0bf-3886-47db-a4ec-f97520da6523.png) 51 | 52 | 53 | - SEEM: Segment Everything Everywhere All at Once [Repo](https://github.com/UX-Decoder/Segment-Everything-Everywhere-All-At-Once) 54 | 55 | ![image](https://user-images.githubusercontent.com/65257938/232041952-4d480b93-56ce-401c-954a-d37e1f72cd5a.png) 56 | 57 | 58 | - Roboflow Annotate Smart Polygon is a free, automated image annotation tool powered by Segment-Anything [Blog](https://blog.roboflow.com/label-data-segment-anything-model-sam/), [App](https://app.roboflow.com) 59 | 60 | https://user-images.githubusercontent.com/870796/231829898-7219aba8-2931-42ae-82a4-9b2a91b02d0a.mp4 61 | 62 | 63 | - Image Editing Anything (SAM + CLIP +StableDiffusion) [Repo](https://github.com/feizc/IEA) 64 | 65 | ![image](https://user-images.githubusercontent.com/65257938/231331898-cfac7986-1638-4059-8bb5-56227256b0a6.png) 66 | 67 | - Semantic Segment Anything (SAM for semantic seg) [Repo](https://github.com/fudan-zvg/Semantic-Segment-Anything) 68 | 69 | ![image](https://user-images.githubusercontent.com/65257938/231338058-34f36f1d-4aad-404d-8c0c-13a5de3b14c0.png) 70 | 71 | 72 | - segment-anything-with-clip (SAM + CLIP) [Repo](https://github.com/Curt-Park/segment-anything-with-clip) 73 | 74 | ![image](https://user-images.githubusercontent.com/65257938/230819815-f20f80db-f234-45e3-a9ce-7638c564ce22.png) 75 | 76 | 77 | - magic-copy (use SAM for foreground mask segmentation) [Repo](https://github.com/kevmo314/magic-copy) 78 | 79 | ![image](https://user-images.githubusercontent.com/65257938/230820035-216af991-6cf5-4207-9a25-40e7564a3cd1.png) 80 | 81 | - EditAnything (SAM for image generation) [Repo](https://github.com/sail-sg/EditAnything) 82 | 83 | ![image](https://user-images.githubusercontent.com/65257938/230915204-70634971-e6cf-4a7c-88f7-388265e9cf3b.png) 84 | 85 | 86 | - Prompt-Segment-Anything (use SAM for instance segmentation) [Repo](https://github.com/RockeyCoss/Prompt-Segment-Anything) 87 | 88 | ![image](https://user-images.githubusercontent.com/65257938/230820059-77098b16-a15e-4563-8a09-919ab49d3a0f.png) 89 | 90 | - RefSAM (use SAM for refer image segmentation) [Repo](https://github.com/helblazer811/RefSAM) 91 | 92 | - sam-mmrotate(use SAM for generating rotated bounding boxes with MMRotate) [Repo](https://github.com/Li-Qingyun/sam-mmrotate) 93 | 94 | ![image](https://user-images.githubusercontent.com/65257938/230820243-c301554b-bccb-477f-aa28-f69865f6afeb.png) 95 | 96 | - Fast-SAM (fast segment-anything) [repo](https://github.com/CASIA-IVA-Lab/FastSAM) 97 | 98 | ![image](https://github.com/JerryX1110/awesome-segment-anything-extensions/assets/65257938/3e8deb90-5f58-425d-951d-96c7c3a16461) 99 | 100 | - Mobile-SAM (faster segment-anything) [repo](https://github.com/ChaoningZhang/MobileSAM) 101 | 102 | ![image](https://github.com/JerryX1110/awesome-segment-anything-extensions/assets/65257938/4731bec8-fd46-4ccf-9286-645efc4f0546) 103 | 104 | 105 | 106 | - Disappear(use SAM for foreground removal) [Repo](https://github.com/jinfagang/Disappear) 107 | 108 | ![image](https://user-images.githubusercontent.com/65257938/230820344-18c7d48c-3704-4c91-b93a-e4999e1b9539.png) 109 | 110 | - Segment-anything-with-image-captioning(sam + image caption) [Repo](https://github.com/bnabis93/segment-anything-image-search) 111 | 112 | 113 | - Open-vocabulary-Segment-Anything (OWL-ViT of Google + Segment Anything of Meta) [Repo](https://github.com/ngthanhtin/owlvit_segment_anything) 114 | 115 | ![image](https://user-images.githubusercontent.com/65257938/230872515-7ea34489-2422-4bcf-aa05-1dd6adbb420c.png) 116 | 117 | - semantic drawing with Segment Anything Model (SAM for mask drawing/editing) [Repo](https://github.com/lujiazho/SegDrawer) 118 | 119 | ![image](https://user-images.githubusercontent.com/65257938/230872776-454f7d84-995f-45b3-9586-315199c8aa72.png) 120 | 121 | - Annotation-anything-pipeline (GPT+SAM) [Repo](https://github.com/Yuqifan1117/Annotation-anything-pipeline) 122 | ![image](https://user-images.githubusercontent.com/65257938/230908343-be5840bc-d824-4cbd-b881-9842e2d23844.png) 123 | 124 | - MOTSAM (MOT+SAM->MOTS)[Repo](https://github.com/BingfengYan/MOTSAM) 125 | 126 | - SAMCOD (SAM for Camouflaged Object Detection) [Paper](https://arxiv.org/abs/2304.04709) [Repo](https://github.com/luckybird1994/SAMCOD) 127 | 128 | - Segment Anything Model (SAM) in Napari (SAM + Napari) [Repo](https://github.com/MIC-DKFZ/napari-sam) 129 | 130 | ![image](https://user-images.githubusercontent.com/65257938/231332215-abacbf73-f2af-4ec9-a36f-0d6d973406ee.png) 131 | 132 | - inpainting-anything (SAM + inpainting) [Repo](https://github.com/geekyutao/Inpaint-Anything) 133 | 134 | ![image](https://user-images.githubusercontent.com/65257938/231332320-d8d43a47-e416-404a-bab9-a4bfc7bf82f3.png) 135 | 136 | - segment-anything-eo (Earth observation tools for Meta AI Segment Anything) [Repo](https://github.com/aliaksandr960/segment-anything-eo) 137 | 138 | ![image](https://user-images.githubusercontent.com/65257938/231364402-c98bd73f-5d95-4d46-8904-7a92d24c297c.png) 139 | 140 | - Segment Anything for Stable Diffusion Webui (helping stable diffusion webui users to use segment anything to do stable diffusion inpainting) [Repo]() 141 | 142 | ![image](https://user-images.githubusercontent.com/65257938/231364701-54314d6b-2a93-4485-a266-9ccb20247839.png) 143 | 144 | - Napari plugin of Segment Anything Model (SAM) [Repo] (https://github.com/JoOkuma/napari-segment-anything) 145 | 146 | ![image](https://user-images.githubusercontent.com/65257938/231364852-7af40363-e733-4bc6-9c42-e7411e105702.png) 147 | 148 | - segment-anything-and-name-it (Visual GPT + SAM) [Repo](https://github.com/Cheems-Seminar/segment-anything-and-name-it) 149 | 150 | ![image](https://user-images.githubusercontent.com/65257938/231365544-b88a8628-c396-4263-8d7a-baa1d35717d7.png) 151 | 152 | - AnyLabeling = LabelImg + Labelme + Improved UI + Auto-labeling [Repo](https://github.com/vietanhdev/anylabeling) 153 | 154 | ![image](https://user-images.githubusercontent.com/65257938/231440358-7a02df55-b578-4f82-b97e-42f9f8d93373.png) 155 | 156 | - Caption-anything (Segment Anything + Visual Captioning + ChatGPT) [Repo](https://github.com/ttengwang/Caption-Anything) 157 | 158 | ![image](https://user-images.githubusercontent.com/65257938/231440778-d1ae3cf3-a0ba-448c-adfe-a6fa1648ee20.png) 159 | 160 | - Segment-anything-u-specify (using sam + clip to segment anything u specify) [Repo](https://github.com/MaybeShewill-CV/segment-anything-u-specify) 161 | 162 | ![image](https://user-images.githubusercontent.com/65257938/231503241-989932a2-0d9a-4d5c-9f0f-e376c4142f04.png) 163 | 164 | - OCR-SAM (SAM for Text, Text Removal and Text Inpainting) [Repo](https://github.com/yeungchenwa/OCR-SAM) 165 | 166 | ![image](https://user-images.githubusercontent.com/65257938/231627848-0bc2b802-d273-4dce-875f-719db28fc7f2.png) 167 | 168 | ![image](https://user-images.githubusercontent.com/65257938/231628050-286362f5-4bf9-40b5-9bfb-a3610c40eba9.png) 169 | 170 | 171 | - finetune-anything (fine-tuning of SAM ) [Repo]() 172 | 173 | ![image](https://user-images.githubusercontent.com/65257938/231627697-4d74bab5-12ea-47b5-afd6-e03635e7ebba.png) 174 | 175 | 176 | - grounded-segment-anything-colab [Repo](https://github.com/camenduru/grounded-segment-anything-colab) 177 | 178 | ![image](https://user-images.githubusercontent.com/65257938/231627733-cc0787ec-d64b-46a2-b2d1-19b6c2c196e9.png) 179 | 180 | 181 | - SAM Medical Imaging [Repo](https://github.com/amine0110/SAM-Medical-Imaging) 182 | 183 | ![image](https://user-images.githubusercontent.com/65257938/231628357-e004ee33-32a0-4f4b-9ec4-63a2bc3a6ea5.png) 184 | 185 | - Segment Anything Prompt (SAM + GroundDINO + Stable Diffusion for foreground removal and background inpainting) [Repo](https://github.com/jinfagang/SegAnythingPro) 186 | 187 | ![image](https://user-images.githubusercontent.com/65257938/231687136-b4a393ff-c5e1-4812-9296-7d7aa656283e.png) 188 | 189 | - Transform Image Into Unique Paragraph (ChatGPT+SAM+BLIP) [Repo](https://github.com/showlab/Image2Paragraph) 190 | 191 | ![image](https://user-images.githubusercontent.com/65257938/231750419-7194770c-30a2-417d-8467-3901c8a8f3e0.png) 192 | 193 | 194 | - LIME-SAM (SAM + Explainable Artificial Intelligence) [Repo](https://github.com/jaydeep-work/LIME-SAM) 195 | 196 | ![image](https://user-images.githubusercontent.com/65257938/231751670-474c8e4f-15f3-4e34-bc12-e28052b3c717.png) 197 | 198 | - sam-with-mmdet (SAM+MMDetection) [Repo](https://github.com/liuyanyi/sam-with-mmdet) 199 | 200 | ![image](https://user-images.githubusercontent.com/65257938/231974436-64a1b6f2-70d0-4cc0-a963-67a4ad39def8.png) 201 | 202 | - open-tracking (sam + tracking) [Repo](https://github.com/open-mmlab/playground/#-open-tracking) 203 | 204 | ![image](https://user-images.githubusercontent.com/65257938/231975263-4d4e33f8-1429-437a-9325-70cf4acc8731.png) 205 | 206 | - 3D-Box via Segment Anything (sam for 3D Detection) [Repo](https://github.com/dvlab-research/3D-Box-Segment-Anything) 207 | 208 | ![image](https://user-images.githubusercontent.com/65257938/232042932-f9f9ff65-e2d1-4bbf-92ec-1e40ceb813bf.png) 209 | 210 | - Anything-3D (Segment-Anything + 3D. Let's lift the anything to 3D) [Repo](https://github.com/Anything-of-anything/Anything-3D) 211 | 212 | ![image](https://user-images.githubusercontent.com/65257938/232356082-25300903-299c-451f-aeb8-902e08ed44ed.png) 213 | 214 | ![image](https://user-images.githubusercontent.com/65257938/232356106-b6036694-c734-4f0d-8faf-434f6b2f773d.png) 215 | 216 | - Transfer-Any-Style (SAM for style transfer) [Repo](https://github.com/Anything-of-anything/Transfer-Any-Style) 217 | 218 | ![image](https://user-images.githubusercontent.com/65257938/232356280-d16793b5-f6d7-4ec1-b77a-ef3e0791454c.png) 219 | 220 | 221 | - Paint-anything (sam for drawing) [Repo](https://github.com/Huage001/Paint-Anything) 222 | 223 | ![image](https://user-images.githubusercontent.com/65257938/232356394-7727d33a-8d1f-4b92-9c5e-4ef6c6663d26.png) 224 | 225 | - track-anything (VOS + sam)[Repo](https://github.com/gaomingqi/Track-Anything) 226 | 227 | ![image](https://user-images.githubusercontent.com/65257938/232747440-cce172e1-c7bf-4ecc-9e60-b04f072af16c.png) 228 | 229 | - SAM-medical (SAM for medocal image segmentation)[Repo](https://github.com/hitachinsk/SAM-Medical) 230 | 231 | - relate-anything (relation empowered via SAM) [Repo](https://github.com/Luodian/RelateAnything) 232 | 233 | ![image](https://user-images.githubusercontent.com/65257938/234733689-b4adcf38-b991-4c18-b769-f59148815e65.png) 234 | 235 | - Count Anything (SAM for counting) [Repo](https://github.com/ylqi/Count-Anything) 236 | 237 | ![image](https://user-images.githubusercontent.com/65257938/234733985-7c596be4-deb7-4531-a2cb-6077d03b7157.png) 238 | 239 | - ShowAnything (SAM + SD for editing) [Repo](https://github.com/showlab/ShowAnything) 240 | 241 | ![image](https://user-images.githubusercontent.com/65257938/234734142-06a58f22-3823-4027-a34a-2b25c7e7a9d9.png) 242 | 243 | - MedSAM (SAM for medicine, training tutorial) [Repo](https://github.com/bowang-lab/MedSAM#model-training-video-tutorial) 244 | 245 | - Personalize-SAM (Personalize Segment Anything with 1 Shot in 10 Seconds) [Repo](https://github.com/ZrrSkywalker/Personalize-SAM) 246 | ![image](https://user-images.githubusercontent.com/65257938/236376431-cf9d1c17-c37b-4742-9660-3abcb9f606ef.png) 247 | 248 | 249 | - Segment Any Moving Object with Moving Ego Vehicle (SAM for multi-object segmentation) [arXiv](https://arxiv.org/pdf/2305.00126.pdf) 250 | ![image](https://user-images.githubusercontent.com/65257938/236713942-7c0a8f38-7269-4c5b-9cdf-ae59ac5b95c2.png) 251 | 252 | - Customized Segment Anything Model for Medical Image Segmentation (SAM+LoRA fot Medical Segmentation) [ArXiv](https://arxiv.org/pdf/2304.13785.pdf) 253 | 254 | ![image](https://user-images.githubusercontent.com/65257938/236968547-0b4615dc-5fe0-46b0-9c66-a9bf97cee5a8.png) 255 | 256 | 257 | - Instruct to Act (SAM+OpenCLIP for robotics application) [Repo](https://github.com/OpenGVLab/Instruct2Act) 258 | 259 | ![image](https://github.com/JerryX1110/awesome-segment-anything-extensions/assets/65257938/10a80ded-4799-48af-947b-e09f52e5353b) 260 | 261 | - finetune-anything (SAM finetuning) [Repo](https://github.com/ziqi-jin/finetune-anything) 262 | 263 | ![image](https://github.com/JerryX1110/awesome-segment-anything-extensions/assets/65257938/ca0cd7a7-8fd8-40c4-8388-e2f099f3df3a) 264 | 265 | - SAMScore (semantic Structural Similarity Metric for Image Translation Evaluation) [ArXiv](https://arxiv.org/pdf/2305.15367.pdf) 266 | 267 | ![image](https://github.com/JerryX1110/awesome-segment-anything-extensions/assets/65257938/5e7ecb0f-aee9-4982-9994-b0ad6637c4c3) 268 | 269 | - Detect-AnyShadow (SAM for shadow det) [Repo](https://github.com/harrytea/Detect-AnyShadow) 270 | 271 | ![image](https://github.com/JerryX1110/awesome-segment-anything-extensions/assets/65257938/7b004296-1e5e-4757-b5d4-a1b018a1ce78) 272 | 273 | - SAD: Segment Any RGBD (SAM+Depth / SAM for RGBD) [Repo](https://github.com/Jun-CEN/SegmentAnyRGBD) 274 | 275 | ![image](https://github.com/JerryX1110/awesome-segment-anything-extensions/assets/65257938/9654dc99-faaa-47c9-b0ab-6ff113ce4968) 276 | 277 | - SAM-HQ: Segment Anything in High Quality (High Quality Mask with SAM) [Repo](https://github.com/SysCV/SAM-HQ) 278 | 279 | ![image](https://github.com/JerryX1110/awesome-segment-anything-extensions/assets/65257938/26e015f7-b3b7-4bb4-9915-be8be86361fb) 280 | 281 | - Calib-anything (SAM for calibration optimization) [Repo](https://github.com/OpenCalib/CalibAnything) 282 | 283 | ![image](https://github.com/JerryX1110/awesome-segment-anything-extensions/assets/65257938/f0495544-8e1c-47ad-868a-eb26cf6b2a20) 284 | 285 | 286 | ## Relevant Repos 287 | 288 | - Towards Segmenting Anything That Moves [Repo](https://github.com/achalddave/segment-any-moving) 289 | 290 | ![image](https://user-images.githubusercontent.com/65257938/231467307-93900825-e436-4847-a16f-8fc6d692666e.png) 291 | 292 | - SegGPT: Segmenting Everything In Context [Repo](https://github.com/baaivision/Painter) 293 | 294 | ![image](https://user-images.githubusercontent.com/65257938/231467850-cae7c7cd-21b6-49df-8c5d-fddd405f24ea.png) 295 | 296 | - Painter [Repo](https://github.com/baaivision/Painter) 297 | 298 | ![image](https://user-images.githubusercontent.com/65257938/231469147-eb3709a2-08ea-4320-a461-7589a4950683.png) 299 | 300 | 301 | - Stable Diffusion (High-Resolution Image Synthesis with Latent Diffusion Models) [Repo](https://github.com/CompVis/stable-diffusion) 302 | 303 | ![image](https://user-images.githubusercontent.com/65257938/231468134-747e79ae-9325-4d63-b5a3-ad6676d92757.png) 304 | 305 | - ControlNet (Adding Conditional Control to Text-to-Image Diffusion Models.) [Repo](https://github.com/lllyasviel/ControlNet) [Paper](https://arxiv.org/abs/2302.05543) 306 | 307 | ![image](https://user-images.githubusercontent.com/65257938/231468301-ca80309b-1c01-474b-9631-c8297784d611.png) 308 | 309 | - image2text powered by CLIP and BLIP [Repo](https://github.com/pharmapsychotic/clip-interrogator) 310 | 311 | 312 | 313 | 314 | --------------------------------------------------------------------------------