ICON
agi2nerf
| ICON | agi2nerf | |
|---|---|---|
| 6 | 5 | |
| 1,542 | 106 | |
| - | - | |
| 4.1 | 0.0 | |
| 5 months ago | 8 months ago | |
| Python | Python | |
| GNU General Public License v3.0 or later | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ICON
- ControlNet fully integrated with Blender using nodes!
- Is there any AI that can compile several pictures of a person into a single, 3d version?
-
[R][P] ICON: Implicit Clothed humans Obtained from Normals + Gradio Web Demo
github: https://github.com/YuliangXiu/ICON
- Show HN: Icon-3D Avatar Creator from 2D Pixels
-
Icon: Towards Large-Scale Avatar Creation from In-the-Wild Pixels
Realistic virtual humans will play a central role in mixed and augmented reality, forming a critical foundation for the Metaverse and supporting remote presence, collaboration, education, and entertainment.
To enable this, new tools are needed to easily create large-scale 3D virtual humans that can be readily animated. However, current methods need either posed 3D scans captured by expensive scanning equipment or 2D images with carefully controlled user poses. Both of them can't scale up easily.
ICON ("Implicit Clothed humans Obtained from Normals") takes a step towards robust 3D clothed human reconstruction from in-the-wild images. This also enables creating animatable avatars directly from video with personalized and natural pose-dependent cloth deformation.
Homepage: https://icon.is.tue.mpg.de/
Github: https://github.com/YuliangXiu/ICON
Google Colab: https://colab.research.google.com/drive/1-AWeWhPvCTBX0KfMtgt...
agi2nerf
-
Camera Track to NERF
Agisoft: https://github.com/EnricoAhlers/agi2nerf
- Instant NeRF of the Palm House, Kew Gardens. Made with NVIDIA Instant NGP and the Insta360 RS 1-Inch 360.
- Rooftop DJing 🎛🕺🏽 NeRF breathes new life into "moment" captures like this — turning old drone clips less into 3d models, and more into 3d memories
-
I wrote a script for converting Metashape projects to nerfs (Neural Radiance Fields)
Recently I have been experimenting with Nvidia's Instant NGP. They include a script for converting COLMAP saves to nerfs but COLMAP is really bad in my opinion. You can find my script for converting Metashape camera positions to a nerf save here. If you have any questions or feature requests please let me know!
-
can someone help me setup an nvidia nerf generator locally? a step by step video would be so helpful, I am not a coder or anything
If you get it running you can also use this tool I wrote to convert Agisoft Metashape saves to nerfs.
What are some alternatives?
lightweight-human-pose-estimation.pytorch - Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.
instant-ngp - Instant neural graphics primitives: lightning fast NeRF and more
ECON - [CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration
BlenderProc - A procedural Blender pipeline for photorealistic training image generation
dream-textures - Stable Diffusion built-in to Blender
Meshroom - 3D Reconstruction Software
AlphaPose - Real-Time and Accurate Full-Body Multi-Person Pose Estimation&Tracking System
IGR - Implicit Geometric Regularization for Learning Shapes
text2cinemagraph - Text2Cinemagraph: Text-Guided Synthesis of Eulerian Cinemagraphs [SIGGRAPH ASIA 2023]
BlenderNeRF - Easy NeRF synthetic dataset creation within Blender
aistplusplus_api - API to support AIST++ Dataset: https://google.github.io/aistplusplus_dataset