Focus stacking code

A visualization tool for analyzing preprocessing results of WAI/Nerfstudio format datasets containing RGB images and corresponding depth maps to generate interactive 3D visualizations.

🌊 Images to → 3D Parallax effect video. A free and open source ImmersityAI alternative

Real-time ADAS using MiDaS depth estimation and YOLO object detection for collision alerts, lane departure warnings, and intuitive visual/audio feedback.

Multi-sensor RealSense + YOLO Top-View People Counting System, developed within the MEI (Museo Egizio Immersive) project. The solution enables real-time detection and counting of people in defined spatial areas, driving immersive scene logic, lighting systems, and audience analytics for interactive museum installations in Unreal Engine 5.

3D-Image-Toolbox is a Python-based tool that transforms images and videos into immersive spatial experiences. Using depth-anything-v2 model, it generates depth maps from standard 2D media and converts them into side-by-side 3D formats. From spacial photos (heic format) it uses the contained depth map.

ComfyUI Depth Anything (v1/v2/distill-any-depth) Tensorrt Custom Node (up to 14x faster)

This project estimates the distance to objects using stereo vision and depth maps

This may turn out useful if you happen to have a photometric stereo scanner or if you want to create other mappings from a given normal map.

Official code for the paper: Depth Anything At Any Condition

Open vocabulary object segmentation on depth map

DepthLight is a novel method to represent estimated spatial lighting with an emissive texture mesh, producing a simple and lightweight 3D representation for photorealistic object relighting.

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

Code for my point cloud completion paper in CVF-ICCV2017

Depth-Anything2-based generalized depth extraction and TensorRT test

Depth map estimation tool using Depth-Anything-V2. Generate accurate depth maps from images with support for both relative and metric depth measurements.

Synthetic Depth Data Generation Using Simulated Annealing (on Body Tracking Modality)

This project explores generating high-quality images using depth maps and conditioning techniques like Canny edges, leveraging Stable Diffusion and ControlNet models. It focuses on optimizing image generation with different aspect ratios, inference steps to balance speed and quality.

Comprehensive beginner's guide to computer vision with user-friendly Python scripts using OpenCV, covering essential topics and providing step-by-step tutorials.

Evaluation code for the investigation of iPad TrueDepth data issues.