Sam Hq Vit Huge

🚀 Model Card for Segment Anything Model in High Quality (SAM-HQ)

SAM-HQ (Segment Anything in High Quality) is an enhanced version of the Segment Anything Model (SAM). It can generate higher - quality object masks from input prompts like points or boxes. While SAM was trained on a large dataset, its mask prediction quality has limitations, especially for objects with complex structures. SAM - HQ addresses these issues with minimal additional parameters and computation cost.

🚀 Quick Start

SAM-HQ is an advanced model for generating high - quality segmentation masks. It builds on the original SAM architecture and can be used in various scenarios such as prompted - mask - generation and automatic - mask - generation.

✨ Features

• High - Quality Output Token: A learnable token in the mask decoder, trained to predict high - quality masks.
• Global - local Feature Fusion: Fuses features from different stages of ViT for more accurate segmentation, combining high - level semantic context and low - level boundary information.
• Improved Mask Quality: Produces better masks, especially for objects with complex boundaries and thin structures, while maintaining SAM's original promptable design, efficiency, and zero - shot generalizability.

📦 Installation

The README does not provide specific installation steps, so this section is skipped.

💻 Usage Examples

Basic Usage

Prompted - Mask - Generation

from PIL import Image
import requests
from transformers import SamHQModel, SamHQProcessor

model = SamHQModel.from_pretrained("syscv-community/sam-hq-vit-huge")
processor = SamHQProcessor.from_pretrained("syscv-community/sam-hq-vit-huge")

img_url = "https://raw.githubusercontent.com/SysCV/sam-hq/refs/heads/main/demo/input_imgs/example1.png"
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert("RGB")
input_boxes = [[[306, 132, 925, 893]]]  # Bounding box for the image

inputs = processor(raw_image, input_boxes=input_boxes, return_tensors="pt").to("cuda")
outputs = model(**inputs)
masks = processor.image_processor.post_process_masks(outputs.pred_masks.cpu(), inputs["original_sizes"].cpu(), inputs["reshaped_input_sizes"].cpu())
scores = outputs.iou_scores

Automatic - Mask - Generation

from transformers import pipeline
generator = pipeline("mask-generation", model="syscv-community/sam-hq-vit-huge", device=0, points_per_batch=256)
image_url = "https://raw.githubusercontent.com/SysCV/sam-hq/refs/heads/main/demo/input_imgs/example1.png"
outputs = generator(image_url, points_per_batch=256)

Advanced Usage

Complete Example with Visualization

import numpy as np
import matplotlib.pyplot as plt
def show_mask(mask, ax, random_color=False):
    if random_color:
        color = np.concatenate([np.random.random(3), np.array([0.6])], axis=0)
    else:
        color = np.array([30/255, 144/255, 255/255, 0.6])
    h, w = mask.shape[-2:]
    mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)
    ax.imshow(mask_image)
def show_box(box, ax):
    x0, y0 = box[0], box[1]
    w, h = box[2] - box[0], box[3] - box[1]
    ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0,0,0,0), lw=2))  
def show_boxes_on_image(raw_image, boxes):
    plt.figure(figsize=(10,10))
    plt.imshow(raw_image)
    for box in boxes:
      show_box(box, plt.gca())
    plt.axis('on')
    plt.show()
def show_points_on_image(raw_image, input_points, input_labels=None):
    plt.figure(figsize=(10,10))
    plt.imshow(raw_image)
    input_points = np.array(input_points)
    if input_labels is None:
      labels = np.ones_like(input_points[:, 0])
    else:
      labels = np.array(input_labels)
    show_points(input_points, labels, plt.gca())
    plt.axis('on')
    plt.show()
def show_points_and_boxes_on_image(raw_image, boxes, input_points, input_labels=None):
    plt.figure(figsize=(10,10))
    plt.imshow(raw_image)
    input_points = np.array(input_points)
    if input_labels is None:
      labels = np.ones_like(input_points[:, 0])
    else:
      labels = np.array(input_labels)
    show_points(input_points, labels, plt.gca())
    for box in boxes:
      show_box(box, plt.gca())
    plt.axis('on')
    plt.show()
def show_points_and_boxes_on_image(raw_image, boxes, input_points, input_labels=None):
    plt.figure(figsize=(10,10))
    plt.imshow(raw_image)
    input_points = np.array(input_points)
    if input_labels is None:
      labels = np.ones_like(input_points[:, 0])
    else:
      labels = np.array(input_labels)
    show_points(input_points, labels, plt.gca())
    for box in boxes:
      show_box(box, plt.gca())
    plt.axis('on')
    plt.show()
def show_points(coords, labels, ax, marker_size=375):
    pos_points = coords[labels==1]
    neg_points = coords[labels==0]
    ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
    ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)
def show_masks_on_image(raw_image, masks, scores):
    if len(masks.shape) == 4:
      masks = masks.squeeze()
    if scores.shape[0] == 1:
      scores = scores.squeeze()
    nb_predictions = scores.shape[-1]
    fig, axes = plt.subplots(1, nb_predictions, figsize=(15, 15))
    for i, (mask, score) in enumerate(zip(masks, scores)):
      mask = mask.cpu().detach()
      axes[i].imshow(np.array(raw_image))
      show_mask(mask, axes[i])
      axes[i].title.set_text(f"Mask {i+1}, Score: {score.item():.3f}")
      axes[i].axis("off")
    plt.show()
def show_masks_on_single_image(raw_image, masks, scores):
    if len(masks.shape) == 4:
        masks = masks.squeeze()
    if scores.shape[0] == 1:
        scores = scores.squeeze()
    # Convert image to numpy array if it's not already
    image_np = np.array(raw_image)
    # Create a figure
    fig, ax = plt.subplots(figsize=(8, 8))
    ax.imshow(image_np)
    # Overlay all masks on the same image
    for i, (mask, score) in enumerate(zip(masks, scores)):
        mask = mask.cpu().detach().numpy()  # Convert to NumPy
        show_mask(mask, ax)  # Assuming `show_mask` properly overlays the mask
    ax.set_title(f"Overlayed Masks with Scores")
    ax.axis("off")
    plt.show()

import torch
from transformers import SamHQModel, SamHQProcessor

device = "cuda" if torch.cuda.is_available() else "cpu"
model = SamHQModel.from_pretrained("syscv-community/sam-hq-vit-huge").to(device)
processor = SamHQProcessor.from_pretrained("syscv-community/sam-hq-vit-huge")

from PIL import Image
import requests
img_url = "https://raw.githubusercontent.com/SysCV/sam-hq/refs/heads/main/demo/input_imgs/example1.png"
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert("RGB")
plt.imshow(raw_image)

inputs = processor(raw_image, return_tensors="pt").to(device)
image_embeddings, intermediate_embeddings = model.get_image_embeddings(inputs["pixel_values"])

input_boxes = [[[306, 132, 925, 893]]]
show_boxes_on_image(raw_image, input_boxes[0]) 

inputs.pop("pixel_values", None)
inputs.update({"image_embeddings": image_embeddings})
inputs.update({"intermediate_embeddings": intermediate_embeddings})
with torch.no_grad():
    outputs = model(**inputs)
masks = processor.image_processor.post_process_masks(outputs.pred_masks.cpu(), inputs["original_sizes"].cpu(), inputs["reshaped_input_sizes"].cpu())
scores = outputs.iou_scores

show_masks_on_single_image(raw_image, masks[0], scores)

show_masks_on_image(raw_image, masks[0], scores)

📚 Documentation

Model Details

SAM-HQ builds on the original SAM architecture with two key innovations while keeping SAM's pretrained weights:

• High - Quality Output Token: A learnable token in the mask decoder, responsible for predicting high - quality masks. It and its associated MLP layers are specifically trained for accurate segmentation masks.
• Global - local Feature Fusion: Instead of only using the HQ - Output Token on mask - decoder features, SAM - HQ first fuses these features with early and final ViT features to improve mask details.

SAM-HQ was trained on a carefully curated dataset of 44K fine - grained masks (HQSeg - 44K). The training takes only 4 hours on 8 GPUs, with less than 0.5% additional parameters compared to the original SAM model.

The model has been evaluated on 10 diverse segmentation datasets. Results show that SAM - HQ can produce better masks than the original SAM model while maintaining zero - shot generalization capabilities.

Citation

@misc{ke2023segmenthighquality,
      title={Segment Anything in High Quality}, 
      author={Lei Ke and Mingqiao Ye and Martin Danelljan and Yifan Liu and Yu - Wing Tai and Chi - Keung Tang and Fisher Yu},
      year={2023},
      eprint={2306.01567},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2306.01567}, 
}

📄 License

The model is licensed under the apache - 2.0 license.