jcwang0602/MLLMSeg_InternVL2_5_2B_RES

import torch
from PIL import Image
from transformers import AutoModel, AutoTokenizer
import torchvision.transforms as T
from torchvision.transforms.functional import InterpolationMode
import requests
from io import BytesIO

# Define image preprocessing utility functions
IMAGENET_MEAN = (0.485, 0.456, 0.406)
IMAGENET_STD = (0.229, 0.224, 0.225)

def build_transform(input_size):
    MEAN, STD = IMAGENET_MEAN, IMAGENET_STD
    transform = T.Compose([
        T.Lambda(lambda img: img.convert('RGB') if img.mode != 'RGB' else img),
        T.Resize((input_size, input_size), interpolation=InterpolationMode.BICUBIC),
        T.ToTensor(),
        T.Normalize(mean=MEAN, std=STD)
    ])
    return transform

def find_closest_aspect_ratio(aspect_ratio, target_ratios, width, height, image_size):
    best_ratio_diff = float('inf')
    best_ratio = (1, 1)
    area = width * height
    for ratio in target_ratios:
        target_aspect_ratio = ratio[0] / ratio[1]
        ratio_diff = abs(aspect_ratio - target_aspect_ratio)
        if ratio_diff < best_ratio_diff:
            best_ratio_diff = ratio_diff
            best_ratio = ratio
        elif ratio_diff == best_ratio_diff:
            if area > 0.5 * image_size * image_size * ratio[0] * ratio[1]:
                best_ratio = ratio
    return best_ratio

def dynamic_preprocess(image, min_num=1, max_num=12, image_size=448, use_thumbnail=False):
    orig_width, orig_height = image.size
    aspect_ratio = orig_width / orig_height

    target_ratios = set(
        (i, j) for n in range(min_num, max_num + 1) for i in range(1, n + 1) for j in range(1, n + 1) if
        i * j <= max_num and i * j >= min_num)
    target_ratios = sorted(target_ratios, key=lambda x: x[0] * x[1])

    target_aspect_ratio = find_closest_aspect_ratio(
        aspect_ratio, target_ratios, orig_width, orig_height, image_size)

    target_width = image_size * target_aspect_ratio[0]
    target_height = image_size * target_aspect_ratio[1]
    blocks = target_aspect_ratio[0] * target_aspect_ratio[1]

    resized_img = image.resize((target_width, target_height))
    processed_images = []
    for i in range(blocks):
        box = (
            (i % (target_width // image_size)) * image_size,
            (i // (target_width // image_size)) * image_size,
            ((i % (target_width // image_size)) + 1) * image_size,
            ((i // (target_width // image_size)) + 1) * image_size
        )
        split_img = resized_img.crop(box)
        processed_images.append(split_img)
    assert len(processed_images) == blocks
    if use_thumbnail and len(processed_images) != 1:
        thumbnail_img = image.resize((image_size, image_size))
        processed_images.append(thumbnail_img)
    return processed_images

def load_image(image_file, input_size=448, max_num=12):
    if image_file.startswith(('http://', 'https://')):
        response = requests.get(image_file)
        image = Image.open(BytesIO(response.content)).convert('RGB')
    else:
        image = Image.open(image_file).convert('RGB')
    
    transform = build_transform(input_size=input_size)
    images = dynamic_preprocess(image, image_size=input_size, use_thumbnail=True, max_num=max_num)
    pixel_values = [transform(image) for image in images]
    pixel_values = torch.stack(pixel_values)
    return pixel_values

# Load model and tokenizer
model_path = "jcwang0602/MLLMSeg_InternVL2_5_8B_RES"
model = AutoModel.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    low_cpu_mem_usage=True,
    trust_remote_code=True
).eval().cuda()
tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True, use_fast=False)

# Load an example image (replace with your image path or URL)
image_path = "https://github.com/jcwang0602/MLLMSeg/raw/main/assets/res_0.png" # Example image from the repo
pixel_values = load_image(image_path, max_num=6).to(torch.bfloat16).cuda()

# Define the referring expression
question = "Please segment the person in the screenshot."

# Set generation configuration
generation_config = dict(max_new_tokens=1024, do_sample=False, temperature=0.0)

# Generate response and segmentation mask
# The output_segmentation_mask=True parameter is crucial for getting the mask directly.
response, history, pred_mask = model.chat(
    tokenizer, pixel_values, question, generation_config, history=None, return_history=True, output_segmentation_mask=True
)

print(f'User: {question}\
Assistant: {response}')
# `pred_mask` will contain the predicted segmentation mask. It's a torch.Tensor.
# You can save or visualize it. For example, to save it as an image:
# from torchvision.utils import save_image
# save_image(pred_mask.float(), "segmentation_mask.png")

@misc{wang2025unlockingpotentialmllmsreferring,
      title={Unlocking the Potential of MLLMs in Referring Expression Segmentation via a Light-weight Mask Decoder}, 
      author={Jingchao Wang and Zhijian Wu and Dingjiang Huang and Yefeng Zheng and Hong Wang},
      year={2025},
      eprint={2508.04107},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2508.04107}, 
}