Add support for SAM2 and SAM3 (Tracker)

README.md

@@ -323,6 +323,7 @@ You can refine your search by selecting the task you're interested in (e.g., [te
 1. **[DiT](https://huggingface.co/docs/transformers/model_doc/dit)** (from Microsoft Research) released with the paper [DiT: Self-supervised Pre-training for Document Image Transformer](https://huggingface.co/papers/2203.02378) by Junlong Li, Yiheng Xu, Tengchao Lv, Lei Cui, Cha Zhang, Furu Wei.
 1. **[Donut](https://huggingface.co/docs/transformers/model_doc/donut)** (from NAVER), released together with the paper [OCR-free Document Understanding Transformer](https://huggingface.co/papers/2111.15664) by Geewook Kim, Teakgyu Hong, Moonbin Yim, Jeongyeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park.
 1. **[DPT](https://huggingface.co/docs/transformers/master/model_doc/dpt)** (from Intel Labs) released with the paper [Vision Transformers for Dense Prediction](https://huggingface.co/papers/2103.13413) by René Ranftl, Alexey Bochkovskiy, Vladlen Koltun.
+1. **[EdgeTAM](https://huggingface.co/docs/transformers/model_doc/edgetam)** (from Facebook) released with the paper [EdgeTAM: On-Device Track Anything Model](https://huggingface.co/papers/2501.07256) by Chong Zhou, Chenchen Zhu, Yunyang Xiong, Saksham Suri, Fanyi Xiao, Lemeng Wu, Raghuraman Krishnamoorthi, Bo Dai, Chen Change Loy, Vikas Chandra, Bilge Soran.
 1. **[EfficientNet](https://huggingface.co/docs/transformers/model_doc/efficientnet)** (from Google Brain) released with the paper [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://huggingface.co/papers/1905.11946) by Mingxing Tan, Quoc V. Le.
 1. **[ELECTRA](https://huggingface.co/docs/transformers/model_doc/electra)** (from Google Research/Stanford University) released with the paper [ELECTRA: Pre-training text encoders as discriminators rather than generators](https://huggingface.co/papers/2003.10555) by Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning.
 1. **ERNIE-4.5** (from Baidu ERNIE Team) released with the blog post [Announcing the Open Source Release of the ERNIE 4.5 Model Family](https://ernie.baidu.com/blog/posts/ernie4.5/) by the Baidu ERNIE Team.
@@ -424,6 +425,8 @@ You can refine your search by selecting the task you're interested in (e.g., [te
 1. **Sapiens** (from Meta AI) released with the paper [Sapiens: Foundation for Human Vision Models](https://huggingface.co/papers/2408.12569) by Rawal Khirodkar, Timur Bagautdinov, Julieta Martinez, Su Zhaoen, Austin James, Peter Selednik, Stuart Anderson, Shunsuke Saito.
 1. **[SegFormer](https://huggingface.co/docs/transformers/model_doc/segformer)** (from NVIDIA) released with the paper [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://huggingface.co/papers/2105.15203) by Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Ping Luo.
 1. **[Segment Anything](https://huggingface.co/docs/transformers/model_doc/sam)** (from Meta AI) released with the paper [Segment Anything](https://huggingface.co/papers/2304.02643v1.pdf) by Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alex Berg, Wan-Yen Lo, Piotr Dollar, Ross Girshick.
+1. **[Segment Anything 2](https://huggingface.co/docs/transformers/model_doc/sam2)** (from Meta AI) released with the paper [SAM 2: Segment Anything in Images and Videos](https://huggingface.co/papers/2408.00714) by Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman Rädle, Chloe Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross Girshick, Piotr Dollár, Christoph Feichtenhofer.
+1. **[Segment Anything 3](https://huggingface.co/docs/transformers/model_doc/sam3)** (from Meta Superintelligence Labs) released with the paper [SAM 3: Segment Anything with Concepts](https://ai.meta.com/research/publications/sam-3-segment-anything-with-concepts/) by SAM 3D Team, Xingyu Chen, Fu-Jen Chu, Pierre Gleize, Kevin J Liang, Alexander Sax, Hao Tang, Weiyao Wang, Michelle Guo, Thibaut Hardin, Xiang Li, Aohan Lin, Jiawei Liu, Ziqi Ma, Anushka Sagar, Bowen Song, Xiaodong Wang, Jianing Yang, Bowen Zhang, Piotr Dollar, Georgia Gkioxari, Matt Feiszli, Jitendra Malik, Nicolas Carion, Laura Gustafson, Yuan-Ting Hu, Shoubhik Debnath, Ronghang Hu, Didac Suris Coll-Vinent, Chaitanya Ryali, Kalyan Vasudev Alwala, Haitham Khedr, Andrew Huang, Jie Lei, Tengyu Ma, Baishan Guo, Arpit Kalla, Markus Marks, Joseph Greer, Meng Wang, Peize Sun, Roman Rädle, Triantafyllos Afouras, Effrosyni Mavroudi, Katherine Xu, Tsung-Han Wu, Yu Zhou, Liliane Momeni, Rishi Hazra, Shuangrui Ding, Sagar Vaze, Francois Porcher, Feng Li, Siyuan Li, Aishwarya Kamath, Ho Kei Cheng, Piotr Dollar, Nikhila Ravi, Kate Saenko, Pengchuan Zhang, Christoph Feichtenhofer.
 1. **[SigLIP](https://huggingface.co/docs/transformers/main/model_doc/siglip)** (from Google AI) released with the paper [Sigmoid Loss for Language Image Pre-Training](https://huggingface.co/papers/2303.15343) by Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, Lucas Beyer.
 1. **[SmolLM3](https://huggingface.co/docs/transformers/main/model_doc/smollm3) (from Hugging Face) released with the blog post [SmolLM3: smol, multilingual, long-context reasoner](https://huggingface.co/blog/smollm3) by the Hugging Face TB Research team.
 1. **[SmolVLM](https://huggingface.co/docs/transformers/main/model_doc/smolvlm) (from Hugging Face) released with the blog posts [SmolVLM - small yet mighty Vision Language Model](https://huggingface.co/blog/smolvlm) and [SmolVLM Grows Smaller – Introducing the 250M & 500M Models!](https://huggingface.co/blog/smolervlm) by the Hugging Face TB Research team.

docs/snippets/6_supported-models.snippet

@@ -37,6 +37,7 @@
 1. **[DiT](https://huggingface.co/docs/transformers/model_doc/dit)** (from Microsoft Research) released with the paper [DiT: Self-supervised Pre-training for Document Image Transformer](https://huggingface.co/papers/2203.02378) by Junlong Li, Yiheng Xu, Tengchao Lv, Lei Cui, Cha Zhang, Furu Wei.
 1. **[Donut](https://huggingface.co/docs/transformers/model_doc/donut)** (from NAVER), released together with the paper [OCR-free Document Understanding Transformer](https://huggingface.co/papers/2111.15664) by Geewook Kim, Teakgyu Hong, Moonbin Yim, Jeongyeon Nam, Jinyoung Park, Jinyeong Yim, Wonseok Hwang, Sangdoo Yun, Dongyoon Han, Seunghyun Park.
 1. **[DPT](https://huggingface.co/docs/transformers/master/model_doc/dpt)** (from Intel Labs) released with the paper [Vision Transformers for Dense Prediction](https://huggingface.co/papers/2103.13413) by René Ranftl, Alexey Bochkovskiy, Vladlen Koltun.
+1. **[EdgeTAM](https://huggingface.co/docs/transformers/model_doc/edgetam)** (from Facebook) released with the paper [EdgeTAM: On-Device Track Anything Model](https://huggingface.co/papers/2501.07256) by Chong Zhou, Chenchen Zhu, Yunyang Xiong, Saksham Suri, Fanyi Xiao, Lemeng Wu, Raghuraman Krishnamoorthi, Bo Dai, Chen Change Loy, Vikas Chandra, Bilge Soran.
 1. **[EfficientNet](https://huggingface.co/docs/transformers/model_doc/efficientnet)** (from Google Brain) released with the paper [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://huggingface.co/papers/1905.11946) by Mingxing Tan, Quoc V. Le.
 1. **[ELECTRA](https://huggingface.co/docs/transformers/model_doc/electra)** (from Google Research/Stanford University) released with the paper [ELECTRA: Pre-training text encoders as discriminators rather than generators](https://huggingface.co/papers/2003.10555) by Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning.
 1. **ERNIE-4.5** (from Baidu ERNIE Team) released with the blog post [Announcing the Open Source Release of the ERNIE 4.5 Model Family](https://ernie.baidu.com/blog/posts/ernie4.5/) by the Baidu ERNIE Team.
@@ -138,6 +139,8 @@
 1. **Sapiens** (from Meta AI) released with the paper [Sapiens: Foundation for Human Vision Models](https://huggingface.co/papers/2408.12569) by Rawal Khirodkar, Timur Bagautdinov, Julieta Martinez, Su Zhaoen, Austin James, Peter Selednik, Stuart Anderson, Shunsuke Saito.
 1. **[SegFormer](https://huggingface.co/docs/transformers/model_doc/segformer)** (from NVIDIA) released with the paper [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://huggingface.co/papers/2105.15203) by Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M. Alvarez, Ping Luo.
 1. **[Segment Anything](https://huggingface.co/docs/transformers/model_doc/sam)** (from Meta AI) released with the paper [Segment Anything](https://huggingface.co/papers/2304.02643v1.pdf) by Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alex Berg, Wan-Yen Lo, Piotr Dollar, Ross Girshick.
+1. **[Segment Anything 2](https://huggingface.co/docs/transformers/model_doc/sam2)** (from Meta AI) released with the paper [SAM 2: Segment Anything in Images and Videos](https://huggingface.co/papers/2408.00714) by Nikhila Ravi, Valentin Gabeur, Yuan-Ting Hu, Ronghang Hu, Chaitanya Ryali, Tengyu Ma, Haitham Khedr, Roman Rädle, Chloe Rolland, Laura Gustafson, Eric Mintun, Junting Pan, Kalyan Vasudev Alwala, Nicolas Carion, Chao-Yuan Wu, Ross Girshick, Piotr Dollár, Christoph Feichtenhofer.
+1. **[Segment Anything 3](https://huggingface.co/docs/transformers/model_doc/sam3)** (from Meta Superintelligence Labs) released with the paper [SAM 3: Segment Anything with Concepts](https://ai.meta.com/research/publications/sam-3-segment-anything-with-concepts/) by SAM 3D Team, Xingyu Chen, Fu-Jen Chu, Pierre Gleize, Kevin J Liang, Alexander Sax, Hao Tang, Weiyao Wang, Michelle Guo, Thibaut Hardin, Xiang Li, Aohan Lin, Jiawei Liu, Ziqi Ma, Anushka Sagar, Bowen Song, Xiaodong Wang, Jianing Yang, Bowen Zhang, Piotr Dollar, Georgia Gkioxari, Matt Feiszli, Jitendra Malik, Nicolas Carion, Laura Gustafson, Yuan-Ting Hu, Shoubhik Debnath, Ronghang Hu, Didac Suris Coll-Vinent, Chaitanya Ryali, Kalyan Vasudev Alwala, Haitham Khedr, Andrew Huang, Jie Lei, Tengyu Ma, Baishan Guo, Arpit Kalla, Markus Marks, Joseph Greer, Meng Wang, Peize Sun, Roman Rädle, Triantafyllos Afouras, Effrosyni Mavroudi, Katherine Xu, Tsung-Han Wu, Yu Zhou, Liliane Momeni, Rishi Hazra, Shuangrui Ding, Sagar Vaze, Francois Porcher, Feng Li, Siyuan Li, Aishwarya Kamath, Ho Kei Cheng, Piotr Dollar, Nikhila Ravi, Kate Saenko, Pengchuan Zhang, Christoph Feichtenhofer.
 1. **[SigLIP](https://huggingface.co/docs/transformers/main/model_doc/siglip)** (from Google AI) released with the paper [Sigmoid Loss for Language Image Pre-Training](https://huggingface.co/papers/2303.15343) by Xiaohua Zhai, Basil Mustafa, Alexander Kolesnikov, Lucas Beyer.
 1. **[SmolLM3](https://huggingface.co/docs/transformers/main/model_doc/smollm3) (from Hugging Face) released with the blog post [SmolLM3: smol, multilingual, long-context reasoner](https://huggingface.co/blog/smollm3) by the Hugging Face TB Research team.
 1. **[SmolVLM](https://huggingface.co/docs/transformers/main/model_doc/smolvlm) (from Hugging Face) released with the blog posts [SmolVLM - small yet mighty Vision Language Model](https://huggingface.co/blog/smolvlm) and [SmolVLM Grows Smaller – Introducing the 250M & 500M Models!](https://huggingface.co/blog/smolervlm) by the Hugging Face TB Research team.

src/models.js

@@ -6083,13 +6083,8 @@ export class Sam2ImageSegmentationOutput extends ModelOutput {
     }
 }
 
-export class EdgeTamPreTrainedModel extends PreTrainedModel { }
-
-/**
- * EdgeTAM for generating segmentation masks, given an input image
- * and optional 2D location and bounding boxes.
- */
-export class EdgeTamModel extends EdgeTamPreTrainedModel {
+export class Sam2PreTrainedModel extends PreTrainedModel { }
+export class Sam2Model extends Sam2PreTrainedModel {
 
     /**
      * Compute image embeddings and positional image embeddings, given the pixel values of an image.
@@ -6159,6 +6154,8 @@ export class EdgeTamModel extends EdgeTamPreTrainedModel {
         return new Sam2ImageSegmentationOutput(await super._call(model_inputs));
     }
 }
+export class EdgeTamModel extends Sam2Model { } // NOTE: extends Sam2Model
+export class Sam3TrackerModel extends Sam2Model { } // NOTE: extends Sam2Model
 //////////////////////////////////////////////////
 
 
@@ -8242,7 +8239,9 @@ const MODEL_FOR_UNIVERSAL_SEGMENTATION_MAPPING_NAMES = new Map([
 
 const MODEL_FOR_MASK_GENERATION_MAPPING_NAMES = new Map([
     ['sam', ['SamModel', SamModel]],
+    ['sam2', ['Sam2Model', Sam2Model]],
     ['edgetam', ['EdgeTamModel', EdgeTamModel]],
+    ['sam3_tracker', ['Sam3TrackerModel', Sam3TrackerModel]],
 ]);
 
 const MODEL_FOR_CTC_MAPPING_NAMES = new Map([

src/models/image_processors.js

@@ -31,7 +31,8 @@ export * from './pvt/image_processing_pvt.js'
 export * from './qwen2_vl/image_processing_qwen2_vl.js'
 export * from './rt_detr/image_processing_rt_detr.js'
 export * from './sam/image_processing_sam.js'
-export * from './sam2/image_processing_sam2.js';
+export * from './sam2/image_processing_sam2.js'
+export * from './sam3/image_processing_sam3.js'
 export * from './segformer/image_processing_segformer.js'
 export * from './siglip/image_processing_siglip.js'
 export * from './smolvlm/image_processing_smolvlm.js'

src/models/sam2/processing_sam2.js

@@ -1,3 +1,4 @@
 import { SamProcessor } from "../sam/processing_sam.js";
 
-export class Sam2VideoProcessor extends SamProcessor { }
+export class Sam2Processor extends SamProcessor { }
+export class Sam2VideoProcessor extends Sam2Processor { }

src/models/sam3/image_processing_sam3.js

@@ -0,0 +1,2 @@
+
+export { Sam2ImageProcessor as Sam3ImageProcessor } from '../sam2/image_processing_sam2.js';