MapAnything is an end-to-end trained Transformer model that can take multiple modalities as input and directly regress the decomposed metric 3D geometric structure of the scene. This model supports more than 12 different 3D reconstruction tasks, including multi-image SfM, multi-view stereo vision, and monocular metric depth estimation.

Computer VisionSafetensorsEnglish

Distill-Any-Depth is a new SOTA monocular depth estimation model trained using knowledge distillation algorithms.

Computer VisionTransformers

Distill-Any-Depth is a SOTA monocular depth estimation model trained based on knowledge distillation algorithms, capable of efficient and accurate depth estimation.

Computer VisionTransformers

A monocular depth estimation model based on the latent diffusion model, supporting high-resolution image processing

Computer VisionDiffusersEnglish

DepthPro is a monocular depth estimation model capable of predicting depth from a single image.

Computer VisionCoreml

DepthPro is a foundational model for zero-shot metric monocular depth estimation, capable of generating high-resolution, high-precision depth maps.

Computer VisionTransformers

RollingDepth is a video depth estimation method that does not require video models, capable of achieving monocular depth estimation and video depth estimation.

Computer VisionDiffusersEnglish

A zero-shot monocular ranging depth estimation foundation model capable of synthesizing high-resolution depth maps with unparalleled sharpness and high-frequency details

Computer VisionSafetensors

Zero-shot monocular ranging depth estimation foundation model capable of synthesizing high-resolution depth maps with absolute scale prediction independent of camera intrinsics

This is a monocular depth estimation model based on the Apache-2.0 license, suitable for zero-shot depth estimation tasks in wild scenes.

Computer VisionDiffusers

A monocular depth estimation model based on the Apache-2.0 license, suitable for zero-shot depth estimation tasks in wild scenes.

Computer VisionDiffusers

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, offering finer details and stronger robustness.

Computer VisionTransformers

Depth Anything V2 is currently the most powerful Monocular Depth Estimation (MDE) model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, offering finer details and stronger robustness.

Computer VisionTransformers

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, offering finer details and stronger robustness.

Computer VisionTransformers

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on 595,000 synthetically annotated images and over 62 million real unlabeled images, featuring fine details and robustness.

Computer VisionTransformers

ONNX version of Depth Anything V2 Small, designed for Transformers.js, intended for monocular depth estimation tasks.

Computer VisionTransformers

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on a large amount of synthetic and real images, providing fine depth details and high robustness.

Depth Anything V2 is currently the most powerful monocular depth estimation (MDE) model, trained on 595,000 synthetically annotated images and over 62 million real unannotated images.

Depth Anything V2 is currently the most powerful monocular depth estimation model, trained on large-scale synthetic and real images. Compared to V1, it captures finer details and is more robust.

ZoeDepth is a vision model for monocular depth estimation, fine-tuned on the KITTI dataset, capable of achieving zero-shot transfer for metric depth estimation.

Computer VisionTransformers