IGEV
openscene
IGEV | openscene | |
---|---|---|
1 | 3 | |
462 | 549 | |
- | - | |
4.9 | 4.9 | |
2 months ago | 7 months ago | |
Python | Python | |
MIT License | Apache License 2.0 |
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.
IGEV
openscene
-
OPENSCENE can identify objects, materials, affordances, activities, and room types in complex 3D scenes, all using a single model trained without any labeled 3D data
Project website: github.io/openscene
-
Any recent tools for LiDAR segmentation?
Can anyone recommend recent tools/models that are good at segmenting point cloud data? My interest is semantic segmentation. Particularly segmenting objects in streets, such as traffic lanes, road signs, trees, power lines, etc. I tried some bits of conventional style a few years ago (YOLO and lots of 3D labeling and training, which was a pain), but I wanted to see if there is anything new out there. For example, I noticed Esri offers a power line extraction tool. I haven't tried but looks nice. Also, deep learning and language model fusion is really kicking in these days:https://github.com/pengsongyou/openscene.
What are some alternatives?
ONNX-CREStereo-Depth-Estimation - Python scripts performing stereo depth estimation using the CREStereo model in ONNX.
SadTalker - [CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
stereoDepth - single and stereo calibration, disparity calculation.
Torch-Pruning - [CVPR 2023] Towards Any Structural Pruning; LLMs / SAM / Diffusion / Transformers / YOLOv8 / CNNs
CREStereo - Official MegEngine implementation of CREStereo(CVPR 2022 Oral).
VideoMAEv2 - [CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking
RealtimeStereo - Attention-Aware Feature Aggregation for Real-time Stereo Matching on Edge Devices (ACCV, 2020)
Instruct2Act - Instruct2Act: Mapping Multi-modality Instructions to Robotic Actions with Large Language Model
simplerecon - [ECCV 2022] SimpleRecon: 3D Reconstruction Without 3D Convolutions
Painter - Painter & SegGPT Series: Vision Foundation Models from BAAI
Meshroom - 3D Reconstruction Software