AdaBins
Depth-Anything
AdaBins | Depth-Anything | |
---|---|---|
3 | 6 | |
697 | 5,941 | |
- | - | |
0.0 | 8.0 | |
about 2 years ago | 25 days ago | |
Python | Python | |
GNU General Public License v3.0 only | 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.
AdaBins
-
FileNotFoundError
if os.path.exists("AdaBins") is not True: gitclone("https://github.com/shariqfarooq123/AdaBins.git")
-
I DON'T KNOW WHAT I'M DOING: VQGAN+CLIP, limited palette, AdaBins, and RIFE
AdaBins: Depth Estimation using Adaptive Bins * https://github.com/shariqfarooq123/AdaBins * https://arxiv.org/abs/2011.14141
-
Monocular Depth Estimation - Running multiple pre-trained models and looking at the average
I was curious what would happen if I ran a few of these models on the same input and calculated the average. So, I ran (1) [AdaBins](https://github.com/shariqfarooq123/AdaBins) (NYU + KITTI models), (2) [DiverseDepth](https://github.com/YvanYin/DiverseDepth), (3) [MiDaS](https://github.com/intel-isl/MiDaS), and (4) [SGDepth](https://github.com/ifnspaml/SGDepth), and calculated a weighted-average depth prediction.
Depth-Anything
-
Video generation models as world simulators
Depth estimation improved a lot as well e.g. with Depth-Anything [0]. But those are mostly relative depth instead of metric. Also when even converted to metric they still seems have a lot of pointclouds at the edges that have to be pruned - visible in this blog [1]. Looks like those models trained on Lidar or Stereo depthmaps that has this limitations. I think we don't have enough clean training data for 3d unless we maybe train on synthetic data (then we can have plenty, generate realistic scene in Unreal Engine 5 and train on rendered 2d frames)
[0] https://github.com/LiheYoung/Depth-Anything
[1] https://medium.com/@patriciogv/the-state-of-the-art-of-depth...
-
Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
Very interesting work! More details here: https://depth-anything.github.io/
It seems better overall and per parameter than current work, with relative and absolute measurement.
Is there any research people are aware of that provides sub-mm level models? For 3D modeling purposes? Or is "classic" photogrammetry still the best option there?
- FLaNK Stack 29 Jan 2024
What are some alternatives?
Practical-RIFE - We are developing more practical approach for users based on RIFE.
ZoeDepth - Metric depth estimation from a single image
merged_depth - Monocular Depth Estimation - Weighted-average prediction from multiple pre-trained depth estimation models
Weaviate - Weaviate is an open-source vector database that stores both objects and vectors, allowing for the combination of vector search with structured filtering with the fault tolerance and scalability of a cloud-native database.
DiverseDepth - The code and data of DiverseDepth