1 7

shriarulmozhivarman PRO

shriarul5273

shriarul5273

AI & ML interests

None yet

Recent Activity

reacted to theirpost with 🚀 about 11 hours ago

🚀 Releasing gradio-sync3dcompare v0.0.22 — a Gradio custom component for synchronized 3D model comparison 🔁 One component. Side-by-side. Perfectly in sync. ✨ What's included 🗂️ Supports GLB and PLY files 🔵 Renders as point clouds or native meshes 🎥 Synchronized orbit, zoom, and pan across all viewports 📐 Auto point sizing with manual override 🔍 Configurable zoom range and reset controls 📦 pip install gradio-sync3dcompare 🛠️ Built on Gradio 6.10.0 — drops into any gr.Blocks app with a single import. 🤗 Try the live demo on Hugging Face Spaces: https://huggingface.co/spaces/shriarul5273/gradio_sync3d_compare ⭐ GitHub: https://github.com/shriarul5273/Sync3DCompare 🎬 See it in action in the video below. The video shows a real-world comparison of two 3D point clouds reconstructed from stereo depth estimation — one from FoundationStereo and one from RAFTStereo. Both models are exported as GLB files directly from the depth output and loaded side-by-side into the component. Every orbit, zoom, and pan is perfectly mirrored across both viewports, making it easy to spot structural differences between the two reconstructions at any angle. 💬 Feedback on supported formats, rendering features, or comparison workflows is very welcome!

reacted to theirpost with 👍 about 11 hours ago

🚀 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: https://huggingface.co/spaces/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

posted an update about 13 hours ago

View all activity

Organizations

None yet

Posts 2

Post

1278

🚀 Releasing gradio-sync3dcompare v0.0.22 — a Gradio custom component for synchronized 3D model comparison

🔁 One component. Side-by-side. Perfectly in sync.

✨ What's included

🗂️ Supports GLB and PLY files
🔵 Renders as point clouds or native meshes
🎥 Synchronized orbit, zoom, and pan across all viewports
📐 Auto point sizing with manual override
🔍 Configurable zoom range and reset controls

📦 pip install gradio-sync3dcompare

🛠️ Built on Gradio 6.10.0 — drops into any gr.Blocks app with a single import.

🤗 Try the live demo on Hugging Face Spaces: shriarul5273/gradio_sync3d_compare

⭐ GitHub: https://github.com/shriarul5273/Sync3DCompare

🎬 See it in action in the video below.
The video shows a real-world comparison of two 3D point clouds reconstructed from stereo depth estimation — one from FoundationStereo and one from RAFTStereo. Both models are exported as GLB files directly from the depth output and loaded side-by-side into the component. Every orbit, zoom, and pan is perfectly mirrored across both viewports, making it easy to spot structural differences between the two reconstructions at any angle.

💬 Feedback on supported formats, rendering features, or comparison workflows is very welcome!

Post

113

🚀 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