| import time
|
|
|
| import gradio as gr
|
| from typing import List, Callable
|
| from abc import ABC, abstractmethod
|
|
|
|
|
| class AppLayout(ABC):
|
| @abstractmethod
|
| def get_English_note(self) -> gr.Markdown:
|
| pass
|
|
|
| @abstractmethod
|
| def get_Chinese_note(self):
|
| pass
|
|
|
| @abstractmethod
|
| def get_input_components(self) -> List[gr.Component]:
|
| pass
|
|
|
|
|
|
|
| class UncondLayout(AppLayout):
|
|
|
| def get_English_note(self):
|
| return gr.Markdown(
|
| """
|
| **Note:**
|
|
|
| + We generate 4 BRep models from sampled noise in Gaussian distribution.
|
| + The model is trained on ABC dataset with a complexity range of 10~100 surface primitives.
|
| + Compared with the state-of-the-art BRep generation methods, HoLa-BRep has a 20%-40% improvement in the validity ratio of the generated models on both the DeepCAD dataset and the ABC dataset.
|
| + Try to adjust the seed for various results.
|
|
|
| <br>
|
| <br>
|
| <br>
|
| <br>
|
| <br>
|
| <br>
|
| <br>
|
| <br>
|
| """
|
| )
|
|
|
| def get_Chinese_note(self):
|
| return gr.Markdown(
|
| """
|
| **无条件生成介绍:**
|
|
|
| + 我们从高斯分布的采样噪声中生成 4 个 BRep 模型。
|
| + 模型在 ABC 数据集上进行训练，复杂度范围为 10~100 个表面基元。
|
| + 与最先进的 BRep 生成方法相比，HoLa-BRep 在 DeepCAD 数据集和 ABC 数据集上生成模型的有效率提高了 20%-40%。
|
| + 请随意调整采样种子，以获得不同的结果。
|
|
|
| <br>
|
| <br>
|
| <br>
|
| <br>
|
| <br>
|
| <br>
|
| <br>
|
| <br>
|
| """
|
| )
|
|
|
| def get_input_components(self) -> List[gr.Component]:
|
| return [
|
| gr.Number(
|
| label="Seed",
|
| value=int(time.time()),
|
| minimum=0,
|
| maximum=2**31-1,
|
| step=1
|
| ),
|
| ]
|
|
|
|
|
| class TextLayout(AppLayout):
|
|
|
| def get_English_note(self):
|
| return gr.Markdown(
|
| """
|
| **Note:**
|
|
|
| + Text can be either abstract or descriptive.
|
| + We use a frozen gte-large-en-v1.5 to extract the feature from the text description.
|
| + While we use the existing Text2CAD dataset which contains more descriptive text, the out of distribution abstract text prompt also works.
|
|
|
| <br>
|
| <br>
|
| """
|
| )
|
| def get_Chinese_note(self):
|
| return gr.Markdown(
|
| """
|
| **文本条件生成介绍:**
|
|
|
| + HoLa-BRep支持简单抽象的文本和复杂的描述性文本。
|
| + 我们使用冻结的gte-large-en-v1.5从文本描述中提取特征。
|
| + 虽然我们使用的是包含更多复杂描述性文本的Text2CAD 数据集，但HoLa-BRep同样适用于简单抽象的文本输入。
|
| + **当前文本输入仅支持英文，敬请谅解。**
|
|
|
| <br>
|
| """
|
| )
|
|
|
| def get_input_components(self) -> List[gr.Component]:
|
| return [
|
| gr.Textbox(lines = 8,max_length=1024, label="Text"),
|
| ]
|
|
|
|
|
| class PCLayout(AppLayout):
|
|
|
| def get_English_note(self):
|
| return gr.Markdown(
|
| """
|
| **Note:**
|
|
|
| + The input point cloud should be in .ply format with the position in -1~+1 and normal vectors.
|
| + The input point cloud can be either sparse or dense. We will downsample the point cloud into 2048 points.
|
| + After test-time augmentation the validity of the generated B-Rep model can reach ~98%.
|
| + We use a small and trainable PointNet++ to extract the feature from the point cloud.
|
| + This checkpoint is only for a clean point cloud without any noise.
|
| + Point cloud contains less ambiguity and usually yields the best conditional generation results compared to other modalities.
|
| """
|
| )
|
| def get_Chinese_note(self):
|
| return gr.Markdown(
|
| """
|
| **点云条件生成介绍:**
|
|
|
| + HoLa-BRep接受.ply 格式的点云输入，且坐标值应该归一化到-1~+1并带有法向信息。
|
| + HoLa-BRep接受稀疏或密集点云，网络处理点云时会将其降采样到2048 个点。
|
| + 经过测试时增强后点云条件生成的有效性可达98%以上。
|
| + 我们使用一个小型可训练的 PointNet++ 从点云中提取特征。
|
| + 目前开放权重仅支持没有任何噪声的点云。
|
| + 三维点云作为条件输入具有更少的歧义性，与其他条件相比通常能产生最佳的生成结果。
|
| """
|
| )
|
|
|
| def get_input_components(self):
|
| return [
|
| gr.File(
|
| label='PC',
|
| file_count='single',
|
| ),
|
| ]
|
|
|
|
|
| class SketchLayout(AppLayout):
|
|
|
| def get_English_note(self):
|
| return gr.Markdown(
|
| """
|
| **Note:**
|
|
|
| + The input sketch is in 1:1 ratio and on a white background, it will be further downsampled to 224*224 before feeding into the network.
|
| + The input sketch should be a perspective projection rather than an orthogonal projection.
|
| + We use a frozen DINOv2 to extract the feature from the sketch image.
|
| + We obtained the training sketches using wireframe rendering in OpenCascade.
|
|
|
| <br>
|
| <br>
|
| """
|
| )
|
|
|
| def get_Chinese_note(self):
|
| return gr.Markdown(
|
| """
|
| **线框图条件生成介绍:**
|
|
|
| + 输入线框图的长宽比应为1:1，背景为白色，系统处理时会降采样到224*224分辨率。
|
| + 输入的线框图应该是透视投影，而不是正交投影。
|
| + 我们使用冻结的 DINOv2 从线框图图像中提取特征。
|
| + 我们使用 OpenCascade 中的线框渲染来获取训练线框图。
|
|
|
| <br>
|
| <br>
|
| """
|
| )
|
|
|
| def get_input_components(self) -> List[gr.Component]:
|
| return [
|
| gr.Image(
|
| label='Sketch',
|
| type='filepath',
|
| sources=["upload"],
|
| interactive=True,
|
| )
|
| ]
|
|
|
|
|
| class SVRLayout(AppLayout):
|
|
|
| def get_English_note(self):
|
| return gr.Markdown(
|
| """
|
| **Note:**
|
|
|
| + The input image is in 1:1 ratio and on a white background, it will be further downsampled to 224*224 before feeding into the network.
|
| + Keep the object in grey for better generation results.
|
| + We use a frozen DINOv2 to extract the feature from the sketch image.
|
| + We obtained the training images using solid rendering in OpenCascade.
|
|
|
| <br>
|
| <br>
|
| """
|
| )
|
|
|
| def get_Chinese_note(self):
|
| return gr.Markdown(
|
| """
|
| **单视角图片条件生成介绍:**
|
|
|
| + 输入图片的长宽比应为1:1，背景为白色，系统处理时会降采样到224*224分辨率。
|
| + 为了获得更好的生成效果，请将对象保持为灰色。
|
| + 我们使用冻结的 DINOv2 从草图图像中提取特征。
|
| + 我们使用 OpenCascade 中的实体渲染来获取训练图像。
|
|
|
| <br>
|
| <br>
|
| """
|
| )
|
|
|
| def get_input_components(self) -> List[gr.Component]:
|
| return [
|
| gr.Image(
|
| label='Image',
|
| type='filepath',
|
| sources=["upload"],
|
| interactive=True,
|
| ),
|
| ]
|
|
|
|
|
| class MVRLayout(AppLayout):
|
|
|
| def get_English_note(self):
|
| return gr.Markdown(
|
| """
|
| **Note:**
|
|
|
| + Similar to the single-view condition, the input image should be in 1:1 ratio and 4 fixed angles, **see the camera pose schematic**.
|
| + Image features are extracted by a frozen DINOv2 and averaged after adding the positional encoding on the camera **pose** embedding.
|
| """
|
| )
|
|
|
| def get_Chinese_note(self):
|
| return gr.Markdown(
|
| """
|
| **多视角图片条件生成介绍:**
|
|
|
| + 与单视角条件类似，输入图像应为 1:1长宽比和4 个固定角度，**见相机位姿示意图**。
|
| + 图像特征由冻结的 DINOv2 提取，并在对相机**位姿**特征进行位置编码后取平均值。
|
|
|
| """
|
| )
|
|
|
| def get_input_components(self) -> List[gr.Component]:
|
| return [
|
| gr.Image(
|
| label='View1',
|
| type='filepath',
|
| interactive=True,
|
| sources=["upload"]
|
| ),
|
| gr.Image(
|
| label='View2',
|
| type='filepath',
|
| interactive=True,
|
| sources=["upload"]
|
|
|
| ),
|
| gr.Image(
|
| label='View3',
|
| type='filepath',
|
| interactive=True,
|
| sources=["upload"]
|
|
|
| ),
|
|
|
| gr.Image(
|
| label='View4',
|
| type='filepath',
|
| interactive=True,
|
| sources=["upload"]
|
|
|
| ),
|
| ]
|
|
|
