init

.gitignore

@@ -0,0 +1,155 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+

app.py

@@ -0,0 +1,205 @@
+# Not ready to use yet
+import argparse
+import numpy as np
+import gradio as gr
+from omegaconf import OmegaConf
+import torch
+from PIL import Image
+import PIL
+from pipelines import TwoStagePipeline
+from huggingface_hub import hf_hub_download
+import os
+import rembg
+from typing import Any
+import json
+import os
+import json
+import argparse
+
+from model import CRM
+from inference import generate3d
+
+pipeline = None
+rembg_session = rembg.new_session()
+
+
+def check_input_image(input_image):
+    if input_image is None:
+        raise gr.Error("No image uploaded!")
+
+
+def remove_background(
+    image: PIL.Image.Image,
+    rembg_session: Any = None,
+    force: bool = False,
+    **rembg_kwargs,
+) -> PIL.Image.Image:
+    do_remove = True
+    if image.mode == "RGBA" and image.getextrema()[3][0] < 255:
+        # explain why current do not rm bg
+        print("alhpa channl not enpty, skip remove background, using alpha channel as mask")
+        background = Image.new("RGBA", image.size, (0, 0, 0, 0))
+        image = Image.alpha_composite(background, image)
+        do_remove = False
+    do_remove = do_remove or force
+    if do_remove:
+        image = rembg.remove(image, session=rembg_session, **rembg_kwargs)
+    return image
+
+def do_resize_content(original_image: Image, scale_rate):
+    # resize image content wile retain the original image size
+    if scale_rate != 1:
+        # Calculate the new size after rescaling
+        new_size = tuple(int(dim * scale_rate) for dim in original_image.size)
+        # Resize the image while maintaining the aspect ratio
+        resized_image = original_image.resize(new_size)
+        # Create a new image with the original size and black background
+        padded_image = Image.new("RGBA", original_image.size, (0, 0, 0, 0))
+        paste_position = ((original_image.width - resized_image.width) // 2, (original_image.height - resized_image.height) // 2)
+        padded_image.paste(resized_image, paste_position)
+        return padded_image
+    else:
+        return original_image
+
+def add_background(image, bg_color=(255, 255, 255)):
+    # given an RGBA image, alpha channel is used as mask to add background color
+    background = Image.new("RGBA", image.size, bg_color)
+    return Image.alpha_composite(background, image)
+
+
+def preprocess_image(input_image, do_remove_background, force_remove, foreground_ratio, backgroud_color):
+    """
+    input image is a pil image in RGBA, return RGB image
+    """
+    if do_remove_background:
+        image = remove_background(input_image, rembg_session, force_remove)
+    image = do_resize_content(image, foreground_ratio)
+    image = add_background(image, backgroud_color)
+    return image.convert("RGB")
+
+
+def gen_image(input_image, seed, scale, step):
+    global pipeline, model, args
+    pipeline.set_seed(seed)
+    rt_dict = pipeline(input_image, scale=scale, step=step)
+    stage1_images = rt_dict["stage1_images"]
+    stage2_images = rt_dict["stage2_images"]
+    np_imgs = np.concatenate(stage1_images, 1)
+    np_xyzs = np.concatenate(stage2_images, 1)
+
+    glb_path, obj_path = generate3d(model, np_imgs, np_xyzs, args.device)
+    return Image.fromarray(np_imgs), Image.fromarray(np_xyzs), glb_path, obj_path
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument(
+    "--stage1_config",
+    type=str,
+    default="configs/nf7_v3_SNR_rd_size_stroke.yaml",
+    help="config for stage1",
+)
+parser.add_argument(
+    "--stage2_config",
+    type=str,
+    default="configs/stage2-v2-snr.yaml",
+    help="config for stage2",
+)
+
+parser.add_argument("--device", type=str, default="cuda")
+args = parser.parse_args()
+
+crm_path = hf_hub_download(repo_id="Zhengyi/CRM", filename="CRM.pth")
+specs = json.load(open("configs/specs_objaverse_total.json"))
+model = CRM(specs).to(args.device)
+model.load_state_dict(torch.load(crm_path, map_location = args.device), strict=False)
+
+stage1_config = OmegaConf.load(args.stage1_config).config
+stage2_config = OmegaConf.load(args.stage2_config).config
+stage2_sampler_config = stage2_config.sampler
+stage1_sampler_config = stage1_config.sampler
+
+stage1_model_config = stage1_config.models
+stage2_model_config = stage2_config.models
+
+xyz_path = hf_hub_download(repo_id="Zhengyi/CRM", filename="ccm-diffusion.pth")
+pixel_path = hf_hub_download(repo_id="Zhengyi/CRM", filename="pixel-diffusion.pth")
+stage1_model_config.resume = pixel_path
+stage2_model_config.resume = xyz_path
+
+pipeline = TwoStagePipeline(
+    stage1_model_config,
+    stage2_model_config,
+    stage1_sampler_config,
+    stage2_sampler_config,
+    device=args.device,
+    dtype=torch.float16
+)
+
+with gr.Blocks() as demo:
+    gr.Markdown("# CRM: Single Image to 3D Textured Mesh with Convolutional Reconstruction Model")
+    with gr.Row():
+        with gr.Column():
+            with gr.Row():
+                image_input = gr.Image(
+                    label="Image input",
+                    image_mode="RGBA",
+                    sources="upload",
+                    type="pil",
+                )
+                processed_image = gr.Image(label="Processed Image", interactive=False, type="pil", image_mode="RGB")
+            with gr.Row():
+                with gr.Column():
+                    with gr.Row():
+                        do_remove_background = gr.Checkbox(label="Remove Background", value=True)
+                        force_remove = gr.Checkbox(label="Force Remove", value=False)
+                    back_groud_color = gr.ColorPicker(label="Background Color", value="#7F7F7F", interactive=False)
+                    foreground_ratio = gr.Slider(
+                        label="Foreground Ratio",
+                        minimum=0.5,
+                        maximum=1.0,
+                        value=1.0,
+                        step=0.05,
+                    )
+
+                with gr.Column():
+                    seed = gr.Number(value=1234, label="seed", precision=0)
+                    guidance_scale = gr.Number(value=5.5, minimum=0, maximum=20, label="guidance_scale")
+                    step = gr.Number(value=50, minimum=1, maximum=100, label="sample steps", precision=0)
+            text_button = gr.Button("Generate Images")
+        with gr.Column():
+            image_output = gr.Image(interactive=False, label="Output RGB image")
+            xyz_ouput = gr.Image(interactive=False, label="Output CCM image")
+
+            output_model = gr.Model3D(
+                label="Output GLB",
+                interactive=False,
+            )
+            output_obj = gr.File(interactive=False, label="Output OBJ")
+
+    inputs = [
+        processed_image,
+        seed,
+        guidance_scale,
+        step,
+    ]
+    outputs = [
+        image_output,
+        xyz_ouput,
+        output_model,
+        output_obj,
+    ]
+    gr.Examples(
+        examples=[os.path.join("examples", i) for i in os.listdir("examples")],
+        inputs=[image_input],
+    )
+
+    text_button.click(fn=check_input_image, inputs=[image_input]).success(
+        fn=preprocess_image,
+        inputs=[image_input, do_remove_background, force_remove, foreground_ratio, back_groud_color],
+        outputs=[processed_image],
+    ).success(
+        fn=gen_image,
+        inputs=inputs,
+        outputs=outputs,
+    )
+    demo.queue().launch()

configs/nf7_v3_SNR_rd_size_stroke.yaml

@@ -0,0 +1,21 @@
+config:
+# others
+    seed: 1234
+    num_frames: 7
+    mode: pixel
+    offset_noise: true
+# model related
+    models:
+        config: imagedream/configs/sd_v2_base_ipmv_zero_SNR.yaml
+        resume: models/pixel.pth
+# sampler related
+    sampler:
+        target: libs.sample.ImageDreamDiffusion
+        params:
+            mode: pixel
+            num_frames: 7
+            camera_views: [1, 2, 3, 4, 5, 0, 0]
+            ref_position: 6
+            random_background: false
+            offset_noise: true
+            resize_rate: 1.0

configs/specs_objaverse_total.json

@@ -0,0 +1,57 @@
+{
+  "Input": {
+    "img_num": 16,
+    "class": "all",
+    "camera_angle_num": 8,
+    "tet_grid_size": 80,
+    "validate_num": 16,
+    "scale": 0.95,
+    "radius": 3,
+    "resolution": [256, 256]
+  },
+
+  "Pretrain": {
+    "mode": null,
+    "sdf_threshold": 0.1,
+    "sdf_scale": 10,
+    "batch_infer": false,
+    "lr": 1e-4,
+    "radius": 0.5
+  },
+
+  "Train": {
+    "mode": "rnd",
+    "num_epochs": 500,
+    "grad_acc": 1,
+    "warm_up": 0,
+    "decay": 0.000,
+    "learning_rate": {
+      "init": 1e-4,
+      "sdf_decay": 1,
+      "rgb_decay": 1
+    },
+    "batch_size": 4,
+    "eva_iter": 80,
+    "eva_all_epoch": 10,
+    "tex_sup_mode": "blender",
+    "exp_uv_mesh": false,
+    "doub": false,
+    "random_bg": false,
+    "shift": 0,
+    "aug_shift": 0,
+    "geo_type": "flex"
+  },
+
+  "ArchSpecs": {
+    "unet_type": "diffusers",
+    "use_3D_aware": false,
+    "fea_concat": false,
+    "mlp_bias": true
+  },
+
+  "DecoderSpecs": {
+    "c_dim": 32,
+    "plane_resolution": 256
+  }
+}
+

configs/stage2-v2-snr.yaml

@@ -0,0 +1,25 @@
+config:
+# others
+    seed: 1234
+    num_frames: 6
+    mode: pixel
+    offset_noise: true
+    gd_type: xyz
+# model related
+    models:
+        config: imagedream/configs/sd_v2_base_ipmv_chin8_zero_snr.yaml
+        resume: models/xyz.pth
+
+# eval related
+    sampler:
+        target: libs.sample.ImageDreamDiffusionStage2
+        params:
+            mode: pixel
+            num_frames: 6
+            camera_views: [1, 2, 3, 4, 5, 0]
+            ref_position: null
+            random_background: false
+            offset_noise: true
+            resize_rate: 1.0
+
+