From 2d39ccc15c6ebe1f1cf64fb4dc7f3bf1486272c7 Mon Sep 17 00:00:00 2001 From: Zhongang Cai <62529255+caizhongang@users.noreply.github.com> Date: Wed, 13 Jul 2022 18:19:45 +0800 Subject: [PATCH] Bump version to v0.9.0 (#214) * Bump to v0.9.0 * Update READMEs * Create __init__.py * Update __init__.py * Update __init__.py * Fix __init__.py Co-authored-by: yl-1993 --- README.md | 17 +++++++++++------ README_CN.md | 17 +++++++++++------ mmhuman3d/data/__init__.py | 0 mmhuman3d/version.py | 2 +- 4 files changed, 23 insertions(+), 13 deletions(-) create mode 100644 mmhuman3d/data/__init__.py diff --git a/README.md b/README.md index 7f66becc..f16eb812 100644 --- a/README.md +++ b/README.md @@ -42,6 +42,11 @@ https://user-images.githubusercontent.com/62529255/144362861-e794b404-c48f-4ebe- A suite of differentiale visualization tools for human parametric model rendering (including part segmentation, depth map and point clouds) and conventional 2D/3D keypoints are available. ## News +- 2022-07-08: MMHuman3D [v0.9.0](https://github.com/open-mmlab/mmhuman3d/releases/tag/v0.9.0) is released. Major updates include: + - Support SMPL-X estimation with [ExPose](https://expose.is.tue.mpg.de/) for simultaneous recovery of face, hands and body + - Support new body model [STAR](https://star.is.tue.mpg.de/) + - Release of [GTA-Human](https://caizhongang.github.io/projects/GTA-Human/) dataset with SPIN-FT (51.98 mm) and PARE-FT (46.84 mm) baselines! (Official) + - Refactor registration and improve performance of SPIN to 57.54 mm - 2022-05-31: MMHuman3D [v0.8.0](https://github.com/open-mmlab/mmhuman3d/releases/tag/v0.8.0) is released. Major updates include: - Support SmoothNet (added by paper authors) - Fix circular import and up to 2.5x speed up in module initialization @@ -51,10 +56,6 @@ https://user-images.githubusercontent.com/62529255/144362861-e794b404-c48f-4ebe- - Support DeciWatch (added by paper authors) - Add GTA-Human HMR baseline (official release) - Support saving inference results -- 2022-04-01: MMHuman3D [v0.6.0](https://github.com/open-mmlab/mmhuman3d/releases/tag/v0.6.0) is released. Major updates include: - - Add HumanDataCache that requires 96% less RAM during training - - Refactor differentiable renderers and support UV map rendering - - Support slice/concat operations for HumanData ## Benchmark and Model Zoo @@ -67,6 +68,9 @@ Supported body models: - [x] [SMPL](https://smpl.is.tue.mpg.de/) (SIGGRAPH Asia'2015) - [x] [SMPL-X](https://smpl-x.is.tue.mpg.de/) (CVPR'2019) +- [x] [MANO](https://mano.is.tue.mpg.de/) (SIGGRAPH ASIA'2017) +- [x] [FLAME](https://flame.is.tue.mpg.de/) (SIGGRAPH ASIA'2017) +- [x] [STAR](https://star.is.tue.mpg.de/) (ECCV'2020) @@ -82,8 +86,8 @@ Supported methods: - [x] [VIBE](https://github.com/mkocabas/VIBE) (CVPR'2020) - [x] [HybrIK](https://jeffli.site/HybrIK/) (CVPR'2021) - [x] [PARE](https://pare.is.tue.mpg.de/) (ICCV'2021) -- [x] [DeciWatch](https://ailingzeng.site/deciwatch) (arXiv'2022) -- [x] [SmoothNet](https://ailingzeng.site/smoothnet) (arXiv'2022) +- [x] [DeciWatch](https://ailingzeng.site/deciwatch) (ECCV'2022) +- [x] [SmoothNet](https://ailingzeng.site/smoothnet) (ECCV'2022) - [x] [ExPose](https://expose.is.tue.mpg.de) (ECCV'2020) @@ -100,6 +104,7 @@ Supported datasets: - [x] [COCO-WholeBody](https://github.com/jin-s13/COCO-WholeBody) (ECCV'2020) - [x] [CrowdPose](https://github.com/Jeff-sjtu/CrowdPose) (CVPR'2019) - [x] [EFT](https://github.com/facebookresearch/eft) (3DV'2021) +- [x] [GTA-Human](https://caizhongang.github.io/projects/GTA-Human/) (arXiv'2021) - [x] [Human3.6M](http://vision.imar.ro/human3.6m/description.php) (TPAMI'2014) - [x] [InstaVariety](https://github.com/akanazawa/human_dynamics/blob/master/doc/insta_variety.md) (CVPR'2019) - [x] [LSP](https://sam.johnson.io/research/lsp.html) (BMVC'2010) diff --git a/README_CN.md b/README_CN.md index 76caa97c..0687f856 100644 --- a/README_CN.md +++ b/README_CN.md @@ -42,6 +42,11 @@ https://user-images.githubusercontent.com/62529255/144362861-e794b404-c48f-4ebe- 一整套可微的可视化工具支持人体参数化模型的渲染（包括部分分割，深度图以及点云）和传统 2D/3D 关键点的可视化。 ## 最新进展 +- 2022-07-08: MMHuman3D [v0.9.0](https://github.com/open-mmlab/mmhuman3d/releases/tag/v0.9.0) 已经发布. 主要更新包括: + - 支持 SMPL-X 估计方法 [ExPose](https://expose.is.tue.mpg.de/)，同时重建脸、手、身体 + - 支持新的人体参数化模型 [STAR](https://star.is.tue.mpg.de/) + - 开源 [GTA-Human](https://caizhongang.github.io/projects/GTA-Human/) 数据集，以及 SPIN-FT (51.98 mm) 和 PARE-FT (46.84 mm) 基线! (官方开源) + - 重构配准管线并提升SPIN至 57.54 mm - 2022-05-31: MMHuman3D [v0.8.0](https://github.com/open-mmlab/mmhuman3d/releases/tag/v0.8.0) 已经发布. 主要更新包括: - 支持 SmoothNet（由论文作者添加） - 修复循环引用问题，获得最多2.5倍速度提升 @@ -51,10 +56,6 @@ https://user-images.githubusercontent.com/62529255/144362861-e794b404-c48f-4ebe- - 支持DeciWatch（由论文作者添加） - 添加GTA-Human的HMR基线（官方开源） - 支持存储推理结果 -- 2022-04-01: MMHuman3D [v0.6.0](https://github.com/open-mmlab/mmhuman3d/releases/tag/v0.6.0) 已经发布. 主要更新包括: - - 增加HumanDataCache，大幅削减(96%)训练时内存占用 - - 重构可微渲染器并支持UV map渲染 - - HumanData支持slice/concat操作 ## 基准与模型库 @@ -67,6 +68,9 @@ https://user-images.githubusercontent.com/62529255/144362861-e794b404-c48f-4ebe- - [x] [SMPL](https://smpl.is.tue.mpg.de/) (SIGGRAPH Asia'2015) - [x] [SMPL-X](https://smpl-x.is.tue.mpg.de/) (CVPR'2019) +- [x] [MANO](https://mano.is.tue.mpg.de/) (SIGGRAPH ASIA'2017) +- [x] [FLAME](https://flame.is.tue.mpg.de/) (SIGGRAPH ASIA'2017) +- [x] [STAR](https://star.is.tue.mpg.de/) (ECCV'2020) @@ -82,8 +86,8 @@ https://user-images.githubusercontent.com/62529255/144362861-e794b404-c48f-4ebe- - [x] [VIBE](https://github.com/mkocabas/VIBE) (CVPR'2020) - [x] [HybrIK](https://jeffli.site/HybrIK/) (CVPR'2021) - [x] [PARE](https://pare.is.tue.mpg.de/) (ICCV'2021) -- [x] [DeciWatch](https://ailingzeng.site/deciwatch) (arXiv'2022) -- [x] [SmoothNet](https://ailingzeng.site/smoothnet) (arXiv'2022) +- [x] [DeciWatch](https://ailingzeng.site/deciwatch) (ECCV'2022) +- [x] [SmoothNet](https://ailingzeng.site/smoothnet) (ECCV'2022) - [x] [ExPose](https://expose.is.tue.mpg.de) (ECCV'2020) @@ -100,6 +104,7 @@ https://user-images.githubusercontent.com/62529255/144362861-e794b404-c48f-4ebe- - [x] [COCO-WholeBody](https://github.com/jin-s13/COCO-WholeBody) (ECCV'2020) - [x] [CrowdPose](https://github.com/Jeff-sjtu/CrowdPose) (CVPR'2019) - [x] [EFT](https://github.com/facebookresearch/eft) (3DV'2021) +- [x] [GTA-Human](https://caizhongang.github.io/projects/GTA-Human/) (arXiv'2021) - [x] [Human3.6M](http://vision.imar.ro/human3.6m/description.php) (TPAMI'2014) - [x] [InstaVariety](https://github.com/akanazawa/human_dynamics/blob/master/doc/insta_variety.md) (CVPR'2019) - [x] [LSP](https://sam.johnson.io/research/lsp.html) (BMVC'2010) diff --git a/mmhuman3d/data/__init__.py b/mmhuman3d/data/__init__.py new file mode 100644 index 00000000..e69de29b diff --git a/mmhuman3d/version.py b/mmhuman3d/version.py index 3eaa094d..32f19d54 100644 --- a/mmhuman3d/version.py +++ b/mmhuman3d/version.py @@ -1,6 +1,6 @@ # Copyright (c) Open-MMLab. All rights reserved. -__version__ = '0.8.0' +__version__ = '0.9.0' def parse_version_info(version_str):