TensorRT implementation of Depth-Anything V1, V2

ONNX-compatible Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data

This repository is based on shouxieai/tensorRT_Pro, with adjustments to support YOLOv8.

TouchDesigner implementation for Depth Anything and TensorRT monocular depth estimation.

Rankings include: Align3R BetterDepth ChronoDepth CUT3R Deep3D Depth Any Video Depth Anything Depth Pro DepthCrafter Geo4D GRIN L4P M2SVid MASt3R Metric3D Metric-Solver MoGe MonST3R NVDS RollingDepth StereoCrafter SVG UniDepth UniK3D Video Depth Anything

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

Scripts to convert 2D images and videos into Spatial versions

ROS2 Wrapper for DepthAnything V2 model.

An Android app running inference on Depth-Anything and Depth-Anything-V2

Tensorrt codebase to inference in c++ for all major neural arch using onnx

Dataset and benchmark for indoor monocular depth estimation with focus on indoor space types

ROS1 wrapper package of Depth Anything V2

Repository for the Project of Data Driven Machine Perception

Autonomous car powered by the Raspberry Pi with image processing (OpenCV)

Running Depth Anything model on Qualcomm SNPE SDK

image editor with AI models written in C++, running on CPU

Depth Anything V2 run on ONNX and TensorRT with easy UI and deploy Tritonserver

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.