Trending repositories for topic monocular-depth-estimation

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[CVPR'25] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

[MICCAI'2024] EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera

[CVPR 2025] Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

[WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

[CVPR 2025] Video Depth without Video Models

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

[MICCAI'2024] EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera

[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[CVPR'25] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

[CVPR 2025] Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

[WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

[CVPR 2025] Video Depth without Video Models

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

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

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

[CVPR'25] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

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

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

[CVPR 2025] Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera

[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

[CVPR 2025] Video Depth without Video Models

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

TensorRT implementation of Depth-Anything V1, V2

Metric depth estimation from a single image

EndoSLAM Dataset and an Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos: Endo-SfMLearner

Python tools for Generating and working metric 3D depth videos, 3D stereo video, side by side stereo video. Using 3d rendering and monocular depth estimation models and other ML models.

[MICCAI'2024] EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera

ROS2 Wrapper for DepthAnything V2 model.

A curated list of recent monocular depth estimation papers

[CVPR 2025] Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

[WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

[CVPR 2025] Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera

[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Python tools for Generating and working metric 3D depth videos, 3D stereo video, side by side stereo video. Using 3d rendering and monocular depth estimation models and other ML models.

[MICCAI'2024] EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

[CVPR'25] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

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

TensorRT implementation of Depth-Anything V1, V2

ROS2 Wrapper for DepthAnything V2 model.

[CVPR 2025] Video Depth without Video Models

A curated list of recent monocular depth estimation papers

EndoSLAM Dataset and an Unsupervised Monocular Visual Odometry and Depth Estimation Approach for Endoscopic Videos: Endo-SfMLearner

[CVPR 2025] Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

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

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

[WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

Metric depth estimation from a single image

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

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

[CVPR'25] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

Metric depth estimation from a single image

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

Python tools for Generating and working metric 3D depth videos, 3D stereo video, side by side stereo video. Using 3d rendering and monocular depth estimation models and other ML models.

[CVPR 2025] Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera

[CVPR 2025] Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

[CVPR 2025] Video Depth without Video Models

[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

[CVPR 2025] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affine Corrections of Monocular Depth Priors"

Official implementation for HybridDepth Model (WACV 2025, ISMAR 2024)

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

[WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

A curated list of recent monocular depth estimation papers

ROS2 Wrapper for DepthAnything V2 model.

Python tools for Generating and working metric 3D depth videos, 3D stereo video, side by side stereo video. Using 3d rendering and monocular depth estimation models and other ML models.

[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[CVPR 2025] Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera

[CVPR 2025] Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

[CVPR 2025] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affine Corrections of Monocular Depth Priors"

[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

http://arxiv.org/abs/2403.17301

Official implementation for HybridDepth Model (WACV 2025, ISMAR 2024)

ROS2 Wrapper for DepthAnything V2 model.

[CVPR'25] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

A curated list of recent monocular depth estimation papers

Monocular Depth Estimation Toolbox and Benchmark. [Arxiv'24 ScaleDepth, TCSVT'24 Plane2Depth, TIP'24 Binsformer]

Official implementation of RGBManip (ICRA2024)

Rankings include: Align3R BetterDepth Buffer Anytime ChronoDepth CUT3R Deep3D Depth Any Video Depth Anything Depth Pro DepthCrafter Diffusion E2E FT FutureDepth GRIN L4P Metric3D MoGe MonST3R NVDS NVD...

State-of-the-art papers for depth estimation of 360 images.

A toolbox for benchmarking SOTA discriminative and generative geometry estimation models.

[CVPR 2025] Video Depth without Video Models

[MICCAI'2024] EndoDAC: Efficient Adapting Foundation Model for Self-Supervised Depth Estimation from Any Endoscopic Camera

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

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

[CVPR'25] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[CVPR 2025] Video Depth without Video Models

[WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

[CVPR 2025] Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

Official implementation for HybridDepth Model (WACV 2025, ISMAR 2024)

[CVPR 2025] Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera

[CVPR 2025] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affine Corrections of Monocular Depth Priors"

ROS2 Wrapper for DepthAnything V2 model.

Python scripts performing Metric Monocular Depth Estimation using the Unidepth model in ONNX.

[ECCV 2024] Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions

Monocular Depth Estimation Toolbox and Benchmark. [Arxiv'24 ScaleDepth, TCSVT'24 Plane2Depth, TIP'24 Binsformer]

A toolbox for benchmarking SOTA discriminative and generative geometry estimation models.

Python tools for Generating and working metric 3D depth videos, 3D stereo video, side by side stereo video. Using 3d rendering and monocular depth estimation models and other ML models.

[ECCV 2024] Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimation

PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage

Official implementation of RGBManip (ICRA2024)

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

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

[CVPR'25] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

Code for robust monocular depth estimation described in "Ranftl et. al., Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer, TPAMI 2022"

[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

Metric depth estimation from a single image

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

[CVPR 2025] Video Depth without Video Models

[WACV'25 Oral] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

TensorRT implementation of Depth-Anything V1, V2

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

[CVPR'2024] Official implementation of the paper "ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation"

[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

Official implementation for HybridDepth Model (WACV 2025, ISMAR 2024)

[CVPR 2025] Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

Rankings include: Align3R BetterDepth Buffer Anytime ChronoDepth CUT3R Deep3D Depth Any Video Depth Anything Depth Pro DepthCrafter Diffusion E2E FT FutureDepth GRIN L4P Metric3D MoGe MonST3R NVDS NVD...

[CVPR 2025] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affine Corrections of Monocular Depth Priors"

[CVPR 2025] Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera

[CVPR'25] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

[CVPR'2024] Official implementation of the paper "ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation"

[ICLR2025] GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models

Python scripts performing Metric Monocular Depth Estimation using the Unidepth model in ONNX.

Monocular Depth Estimation Toolbox and Benchmark. [Arxiv'24 ScaleDepth, TCSVT'24 Plane2Depth, TIP'24 Binsformer]

Rankings include: Align3R BetterDepth Buffer Anytime ChronoDepth CUT3R Deep3D Depth Any Video Depth Anything Depth Pro DepthCrafter Diffusion E2E FT FutureDepth GRIN L4P Metric3D MoGe MonST3R NVDS NVD...

[CVPR 2025] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[CVPR 2025] Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera

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

[CVPR 2025] Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail

A curated list of recent monocular depth estimation papers

Using PyTorch's MiDaS model and Open3D's point cloud to map a scene in 3D 🏞️🔭

A toolbox for benchmarking SOTA discriminative and generative geometry estimation models.

Monocular Depth Estimation with Unity Sentis

[IPCAI'2024 (IJCARS special issue)] Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery

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

TouchDesigner implementation for Depth Anything and TensorRT monocular depth estimation.

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

State-of-the-art papers for depth estimation of 360 images.

TensorRT implementation of Depth-Anything V1, V2