Post
141
🚀 Releasing depth-estimation v0.1.1 — a unified Python library for monocular depth estimation
One API. 12 model families. 28 variants. The full depth workflow in a single pip install.
Switch between Depth Anything, DepthPro, MoGe, MiDaS, ZoeDepth, VGGT, and more by changing a single string — same preprocessing, same output format, every time.
What's new in v0.1.1 🎨
Introducing depth_estimation.viz — a dedicated visualization toolkit:
🖼️ Display depth maps with show_depth()
🔲 Compare models side-by-side with compare_depths()
🎭 Blend depth over RGB with overlay_depth()
🔴🔵 Generate stereoscopic anaglyphs with create_anaglyph()
🌀 Export rotating 3D surface animations with animate_3d()
🗺️ Inspect per-pixel error heatmaps with plot_error_map()
And since v0.1.0 🎬
Stream depth from video files, webcams, or frame sequences — with EMA temporal smoothing and side-by-side MP4 export.
The full workflow in one place:
✅ Inference (image, batch, CLI)
✅ Video & streaming
✅ Visualization
✅ Fine-tuning with DepthTrainer
✅ Evaluation on NYU, KITTI, DIODE
✅ Dataset loading (auto-download or custom folders)
pip install depth-estimation
🤗 Try the live demo: shriarul5273/Depth-Estimation-Compare-demo
⭐ GitHub: https://github.com/shriarul5273/depth_estimation
Would love to hear what models or features you'd like to see next!
#depthestimation #computervision #deeplearning #python #opensource #pytorch #machinelearning #AI #3Dvision #robotics #autonomousdriving #computationalphotography #imageprocessing #SLAM #pointcloud #stereovisison #neuralnetworks #MLOps #research #huggingface
One API. 12 model families. 28 variants. The full depth workflow in a single pip install.
Switch between Depth Anything, DepthPro, MoGe, MiDaS, ZoeDepth, VGGT, and more by changing a single string — same preprocessing, same output format, every time.
What's new in v0.1.1 🎨
Introducing depth_estimation.viz — a dedicated visualization toolkit:
🖼️ Display depth maps with show_depth()
🔲 Compare models side-by-side with compare_depths()
🎭 Blend depth over RGB with overlay_depth()
🔴🔵 Generate stereoscopic anaglyphs with create_anaglyph()
🌀 Export rotating 3D surface animations with animate_3d()
🗺️ Inspect per-pixel error heatmaps with plot_error_map()
And since v0.1.0 🎬
Stream depth from video files, webcams, or frame sequences — with EMA temporal smoothing and side-by-side MP4 export.
The full workflow in one place:
✅ Inference (image, batch, CLI)
✅ Video & streaming
✅ Visualization
✅ Fine-tuning with DepthTrainer
✅ Evaluation on NYU, KITTI, DIODE
✅ Dataset loading (auto-download or custom folders)
pip install depth-estimation
🤗 Try the live demo: shriarul5273/Depth-Estimation-Compare-demo
⭐ GitHub: https://github.com/shriarul5273/depth_estimation
Would love to hear what models or features you'd like to see next!
#depthestimation #computervision #deeplearning #python #opensource #pytorch #machinelearning #AI #3Dvision #robotics #autonomousdriving #computationalphotography #imageprocessing #SLAM #pointcloud #stereovisison #neuralnetworks #MLOps #research #huggingface