diff --git a/docs/_static/css/readthedocs.css b/docs/_static/css/readthedocs.css
new file mode 100644
index 0000000000..cc61ab82ab
--- /dev/null
+++ b/docs/_static/css/readthedocs.css
@@ -0,0 +1,6 @@
+.header-logo {
+    background-image: url("../image/mmdet3d-logo.png");
+    background-size: 182.5px 40px;
+    height: 40px;
+    width: 182.5px;
+}
diff --git a/docs/_static/image/mmdet3d-logo.png b/docs/_static/image/mmdet3d-logo.png
new file mode 100644
index 0000000000..f4076bd162
Binary files /dev/null and b/docs/_static/image/mmdet3d-logo.png differ
diff --git a/docs/api.rst b/docs/api.rst
index 16e6c9bacd..00153b9151 100644
--- a/docs/api.rst
+++ b/docs/api.rst
@@ -1,6 +1,3 @@
-API Documentation
-=================
-
 mmdet3d.core
 --------------
 
diff --git a/docs/compatibility.md b/docs/compatibility.md
index 06d9d1d616..5cc8dcf84a 100644
--- a/docs/compatibility.md
+++ b/docs/compatibility.md
@@ -1,8 +1,4 @@
-# Compatibility with Previous Versions of MMDetection3D
-
-This document provides detailed descriptions of the BC-breaking changes in MMDetection3D.
-
-## MMDetection3D 0.16.0
+## 0.16.0
 
 ### Returned values of `QueryAndGroup` operation
 
@@ -26,7 +22,7 @@ We adopt a new pre-processing procedure for the ScanNet dataset in order to supp
 
 Please refer to the ScanNet [README.md](https://github.com/open-mmlab/mmdetection3d/blob/master/data/scannet/README.md/) for more details.
 
-## MMDetection3D 0.15.0
+## 0.15.0
 
 ### MMCV Version
 
@@ -45,7 +41,7 @@ We modified the dataset augmentation function `BackgroundPointsFilter`([here](ht
 
 We enhance the pipeline function `IndoorPatchPointSample` used in point cloud segmentation task by adding more choices for patch selection. Also, we plan to remove the unused parameter `sample_rate` in the future. Please modify the code as well as the config files accordingly if you use this transform.
 
-## MMDetection3D 0.14.0
+## 0.14.0
 
 ### Dataset class for 3D segmentation task
 
@@ -65,7 +61,7 @@ We adopt new pre-processing and conversion steps of ScanNet dataset. In previous
 
 We have trained a [VoteNet](https://github.com/open-mmlab/mmdetection3d/blob/master/configs/votenet/votenet_8x8_scannet-3d-18class.py) model on the newly processed ScanNet dataset and get similar benchmark results. In order to prepare ScanNet data for both detection and segmentation tasks, please re-run the new pre-processing scripts following the ScanNet [README.md](https://github.com/open-mmlab/mmdetection3d/blob/master/data/scannet/README.md/).
 
-## MMDetection3D 0.12.0
+## 0.12.0
 
 ### SUNRGBD dataset for ImVoteNet
 
@@ -77,7 +73,7 @@ We adopt a new pre-processing procedure for the SUNRGBD dataset in order to supp
 
 Please refer to the SUNRGBD [README.md](https://github.com/open-mmlab/mmdetection3d/blob/master/data/sunrgbd/README.md/) for more details.
 
-## MMDetection3D 0.6.0
+## 0.6.0
 
 ### VoteNet model structure update
 
diff --git a/docs/conf.py b/docs/conf.py
index 77d1f9548a..ead91b03db 100644
--- a/docs/conf.py
+++ b/docs/conf.py
@@ -11,6 +11,7 @@
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 #
 import os
+import pytorch_sphinx_theme
 import subprocess
 import sys
 from m2r import MdInclude
@@ -48,6 +49,7 @@ def get_version():
     'recommonmark',
     'sphinx_markdown_tables',
     'sphinx.ext.autosectionlabel',
+    'sphinx_copybutton',
 ]
 
 autodoc_mock_imports = [
@@ -80,12 +82,103 @@ def get_version():
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'sphinx_rtd_theme'
+# html_theme = 'sphinx_rtd_theme'
+html_theme = 'pytorch_sphinx_theme'
+html_theme_path = [pytorch_sphinx_theme.get_html_theme_path()]
+
+html_theme_options = {
+    # 'logo_url': 'https://mmocr.readthedocs.io/en/latest/',
+    'menu': [
+        {
+            'name': 'GitHub',
+            'url': 'https://github.com/open-mmlab/mmdetection3d'
+        },
+        {
+            'name':
+            'Projects',
+            'children': [
+                {
+                    'name': 'MMAction2',
+                    'url': 'https://github.com/open-mmlab/mmaction2',
+                },
+                {
+                    'name': 'MMClassification',
+                    'url': 'https://github.com/open-mmlab/mmclassification',
+                },
+                {
+                    'name': 'MMCV',
+                    'url': 'https://github.com/open-mmlab/mmmmcv',
+                },
+                {
+                    'name': 'MMDetection',
+                    'url': 'https://github.com/open-mmlab/mmdetection',
+                },
+                {
+                    'name': 'MMEditing',
+                    'url': 'https://github.com/open-mmlab/mmediting',
+                },
+                {
+                    'name': 'MMGeneration',
+                    'url': 'https://github.com/open-mmlab/mmgeneration',
+                },
+                {
+                    'name': 'MMOCR',
+                    'url': 'https://github.com/open-mmlab/mmocr',
+                },
+                {
+                    'name': 'MMPose',
+                    'url': 'https://github.com/open-mmlab/mmpose',
+                },
+                {
+                    'name': 'MMSegmentation',
+                    'url': 'https://github.com/open-mmlab/mmsegmentation',
+                },
+                {
+                    'name': 'MMTracking',
+                    'url': 'https://github.com/open-mmlab/mmtracking',
+                },
+            ]
+        },
+        {
+            'name':
+            'OpenMMLab',
+            'children': [
+                {
+                    'name': 'Homepage',
+                    'url': 'https://openmmlab.com/'
+                },
+                {
+                    'name': 'GitHub',
+                    'url': 'https://github.com/open-mmlab/'
+                },
+                {
+                    'name': 'Twitter',
+                    'url': 'https://twitter.com/OpenMMLab'
+                },
+                {
+                    'name': 'Zhihu',
+                    'url': 'https://zhihu.com/people/openmmlab'
+                },
+            ]
+        },
+    ]
+}
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
 html_static_path = ['_static']
+html_css_files = ['css/readthedocs.css']
+
+latex_documents = [
+    (master_doc, 'mmcv.tex', 'mmcv Documentation', 'MMCV Contributors',
+     'manual'),
+]
+
+# -- Extension configuration -------------------------------------------------
+# Ignore >>> when copying code
+copybutton_prompt_text = r'>>> |\.\.\. '
+copybutton_prompt_is_regexp = True
 
 
 def builder_inited_handler(app):
diff --git a/docs/index.rst b/docs/index.rst
index dff69a5eed..0d21d0beed 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -2,59 +2,91 @@ Welcome to MMDetection3D's documentation!
 ==========================================
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
    :caption: Get Started
 
    getting_started.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Demo
+
    demo.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Model Zoo
+
    model_zoo.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Data Preparation
+
    data_preparation.md
 
 .. toctree::
-   :maxdepth: 2
-   :caption: Quick Run
+   :maxdepth: 1
+   :caption: Exist Data and Model
 
    1_exist_data_model.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: New Data and Model
+
    2_new_data_model.md
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
    :caption: Supported Tasks
 
    supported_tasks/index.rst
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
    :caption: Datasets
 
    datasets/index.rst
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
    :caption: Tutorials
 
    tutorials/index.rst
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
    :caption: Useful Tools and Scripts
 
    useful_tools.md
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
    :caption: Notes
 
    benchmarks.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: FAQ
+
    faq.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: Compatibility
+
    compatibility.md
 
 .. toctree::
+   :maxdepth: 1
    :caption: API Reference
 
    api.rst
 
 .. toctree::
+   :maxdepth: 1
    :caption: Switch Language
 
    switch_language.md
diff --git a/docs_zh-CN/1_exist_data_model.md b/docs_zh-CN/1_exist_data_model.md
index 52b1f7e076..faae576c92 100644
--- a/docs_zh-CN/1_exist_data_model.md
+++ b/docs_zh-CN/1_exist_data_model.md
@@ -1,4 +1,4 @@
-# 1：使用已有模型在标准数据集上进行推理和训练
+# 1: 使用已有模型在标准数据集上进行推理和训练
 
 ## 使用已有模型进行推理
 
diff --git a/docs_zh-CN/_static/css/readthedocs.css b/docs_zh-CN/_static/css/readthedocs.css
new file mode 100644
index 0000000000..cc61ab82ab
--- /dev/null
+++ b/docs_zh-CN/_static/css/readthedocs.css
@@ -0,0 +1,6 @@
+.header-logo {
+    background-image: url("../image/mmdet3d-logo.png");
+    background-size: 182.5px 40px;
+    height: 40px;
+    width: 182.5px;
+}
diff --git a/docs_zh-CN/_static/image/mmdet3d-logo.png b/docs_zh-CN/_static/image/mmdet3d-logo.png
new file mode 100644
index 0000000000..f4076bd162
Binary files /dev/null and b/docs_zh-CN/_static/image/mmdet3d-logo.png differ
diff --git a/docs_zh-CN/api.rst b/docs_zh-CN/api.rst
index 16e6c9bacd..00153b9151 100644
--- a/docs_zh-CN/api.rst
+++ b/docs_zh-CN/api.rst
@@ -1,6 +1,3 @@
-API Documentation
-=================
-
 mmdet3d.core
 --------------
 
diff --git a/docs_zh-CN/compatibility.md b/docs_zh-CN/compatibility.md
index bcf6f1c845..3b34d36b5c 100644
--- a/docs_zh-CN/compatibility.md
+++ b/docs_zh-CN/compatibility.md
@@ -1 +1 @@
-# 和过去版本的 MMDetection3D 的兼容性
\ No newline at end of file
+## 0.16.0
diff --git a/docs_zh-CN/conf.py b/docs_zh-CN/conf.py
index 77d1f9548a..601c1d7170 100644
--- a/docs_zh-CN/conf.py
+++ b/docs_zh-CN/conf.py
@@ -11,6 +11,7 @@
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 #
 import os
+import pytorch_sphinx_theme
 import subprocess
 import sys
 from m2r import MdInclude
@@ -48,6 +49,7 @@ def get_version():
     'recommonmark',
     'sphinx_markdown_tables',
     'sphinx.ext.autosectionlabel',
+    'sphinx_copybutton',
 ]
 
 autodoc_mock_imports = [
@@ -80,12 +82,103 @@ def get_version():
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-html_theme = 'sphinx_rtd_theme'
+# html_theme = 'sphinx_rtd_theme'
+html_theme = 'pytorch_sphinx_theme'
+html_theme_path = [pytorch_sphinx_theme.get_html_theme_path()]
+
+html_theme_options = {
+    # 'logo_url': 'https://mmocr.readthedocs.io/en/latest/',
+    'menu': [
+        {
+            'name': 'GitHub',
+            'url': 'https://github.com/open-mmlab/mmdetection3d'
+        },
+        {
+            'name':
+            '算法库',
+            'children': [
+                {
+                    'name': 'MMAction2',
+                    'url': 'https://github.com/open-mmlab/mmaction2',
+                },
+                {
+                    'name': 'MMClassification',
+                    'url': 'https://github.com/open-mmlab/mmclassification',
+                },
+                {
+                    'name': 'MMCV',
+                    'url': 'https://github.com/open-mmlab/mmmmcv',
+                },
+                {
+                    'name': 'MMDetection',
+                    'url': 'https://github.com/open-mmlab/mmdetection',
+                },
+                {
+                    'name': 'MMEditing',
+                    'url': 'https://github.com/open-mmlab/mmediting',
+                },
+                {
+                    'name': 'MMGeneration',
+                    'url': 'https://github.com/open-mmlab/mmgeneration',
+                },
+                {
+                    'name': 'MMOCR',
+                    'url': 'https://github.com/open-mmlab/mmocr',
+                },
+                {
+                    'name': 'MMPose',
+                    'url': 'https://github.com/open-mmlab/mmpose',
+                },
+                {
+                    'name': 'MMSegmentation',
+                    'url': 'https://github.com/open-mmlab/mmsegmentation',
+                },
+                {
+                    'name': 'MMTracking',
+                    'url': 'https://github.com/open-mmlab/mmtracking',
+                },
+            ]
+        },
+        {
+            'name':
+            'OpenMMLab',
+            'children': [
+                {
+                    'name': '官网',
+                    'url': 'https://openmmlab.com/'
+                },
+                {
+                    'name': 'GitHub',
+                    'url': 'https://github.com/open-mmlab/'
+                },
+                {
+                    'name': '推特',
+                    'url': 'https://twitter.com/OpenMMLab'
+                },
+                {
+                    'name': '知乎',
+                    'url': 'https://zhihu.com/people/openmmlab'
+                },
+            ]
+        },
+    ]
+}
 
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
 html_static_path = ['_static']
+html_css_files = ['css/readthedocs.css']
+
+latex_documents = [
+    (master_doc, 'mmcv.tex', 'mmcv Documentation', 'MMCV Contributors',
+     'manual'),
+]
+
+# -- Extension configuration -------------------------------------------------
+# Ignore >>> when copying code
+copybutton_prompt_text = r'>>> |\.\.\. '
+copybutton_prompt_is_regexp = True
 
 
 def builder_inited_handler(app):
diff --git a/docs_zh-CN/index.rst b/docs_zh-CN/index.rst
index 0a4718b944..b2ae80dd8d 100644
--- a/docs_zh-CN/index.rst
+++ b/docs_zh-CN/index.rst
@@ -2,59 +2,91 @@ Welcome to MMDetection3D's documentation!
 ==========================================
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
    :caption: 开始你的第一步
 
    getting_started.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 演示
+
    demo.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 模型库
+
    model_zoo.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 数据预处理
+
    data_preparation.md
 
 .. toctree::
-   :maxdepth: 2
-   :caption: 快速启动
+   :maxdepth: 1
+   :caption: 使用现有数据及模型
 
    1_exist_data_model.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 创建新的数据与模型
+
    2_new_data_model.md
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
    :caption: 支持的任务
 
    supported_tasks/index.rst
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
    :caption: 数据集介绍
 
    datasets/index.rst
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
    :caption: 教程
 
    tutorials/index.rst
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
    :caption: 实用工具与脚本
 
    useful_tools.md
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 1
    :caption: 说明
 
    benchmarks.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 常见问题
+
    faq.md
+
+.. toctree::
+   :maxdepth: 1
+   :caption: 兼容性
+
    compatibility.md
 
 .. toctree::
+   :maxdepth: 1
    :caption: 接口文档（英文）
 
    api.rst
 
 .. toctree::
+   :maxdepth: 1
    :caption: 语言切换
 
    switch_language.md
diff --git a/docs_zh-CN/tutorials/customize_runtime.md b/docs_zh-CN/tutorials/customize_runtime.md
index d7dea39d0e..fc07d4bd43 100644
--- a/docs_zh-CN/tutorials/customize_runtime.md
+++ b/docs_zh-CN/tutorials/customize_runtime.md
@@ -1,4 +1,4 @@
-# 教程 5：自定义运行时配置
+# 教程 5: 自定义运行时配置
 
 ## 自定义优化器设置
 
diff --git a/requirements/docs.txt b/requirements/docs.txt
index 40f8c9ff25..988b5ead21 100644
--- a/requirements/docs.txt
+++ b/requirements/docs.txt
@@ -2,7 +2,8 @@ docutils==0.16.0
 m2r
 myst-parser
 opencv-python
+-e git+https://github.com/open-mmlab/pytorch_sphinx_theme.git#egg=pytorch_sphinx_theme
 sphinx==4.0.2
+sphinx-copybutton
 sphinx_markdown_tables
-sphinx_rtd_theme==0.5.2
 torch
diff --git a/setup.cfg b/setup.cfg
index 8b615d27cf..59d03be6de 100644
--- a/setup.cfg
+++ b/setup.cfg
@@ -8,6 +8,6 @@ line_length = 79
 multi_line_output = 0
 known_standard_library = setuptools
 known_first_party = mmdet,mmseg,mmdet3d
-known_third_party = cv2,imageio,indoor3d_util,load_scannet_data,lyft_dataset_sdk,m2r,matplotlib,mmcv,nuimages,numba,numpy,nuscenes,pandas,plyfile,pycocotools,pyquaternion,pytest,recommonmark,scannet_utils,scipy,seaborn,shapely,skimage,tensorflow,terminaltables,torch,trimesh,waymo_open_dataset
+known_third_party = cv2,imageio,indoor3d_util,load_scannet_data,lyft_dataset_sdk,m2r,matplotlib,mmcv,nuimages,numba,numpy,nuscenes,pandas,plyfile,pycocotools,pyquaternion,pytest,pytorch_sphinx_theme,recommonmark,scannet_utils,scipy,seaborn,shapely,skimage,tensorflow,terminaltables,torch,trimesh,waymo_open_dataset
 no_lines_before = STDLIB,LOCALFOLDER
 default_section = THIRDPARTY