Alternatives and similar repositories for Depth-Anything-3

Users that are interested in Depth-Anything-3 are comparing it to the libraries listed below

• UniFlowMatch / UFM
  UFM: A Unified Dense Image Correspondence Estimator for both Optical Flow & Wide Baseline Matching Tasks. Matches any pair of images. (Ne…
  ☆255Updated 2 weeks ago
• ethz-vlg / mvtracker
  [ICCV 2025 Oral] MVTracker: Multi-view 3D Point Tracking
  ☆419Updated last week
• facebookresearch / 4DGT
  [NeurIPS 2025 (Spotlight)] The implementation for the paper "4DGT Learning a 4D Gaussian Transformer Using Real-World Monocular Videos"
  ☆317Updated last month
• Brummi / anycam
  Official repository for "AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos" (CVPR 2025)
  ☆282Updated 6 months ago
• jzr99 / Geo4D
  [ICCV 2025 Highlight] Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction
  ☆378Updated 5 months ago
• naver / must3r
  MUSt3R: Multi-view Network for Stereo 3D Reconstruction
  ☆262Updated last month
• pablovela5620 / mini-dust3r
  ☆270Updated 7 months ago
• weijielyu / Gaga
  Gaga: Group Any Gaussians via 3D-aware Memory Bank
  ☆389Updated 3 months ago
• TencentARC / GeometryCrafter
  [ICCV 2025] GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors
  ☆409Updated last month
• jiah-cloud / Align3R
  [CVPR 2025 Highlight] Align3R: Aligned Monocular Depth Estimation for Dynamic Videos
  ☆445Updated 7 months ago
• Inception3D / Easi3R
  [ICCV 2025] A simple training-free approach adapting DUSt3R for dynamic scenes.
  ☆473Updated 7 months ago
• zbw001 / TAPIP3D
  TAPIP3D: Tracking Any Point in Persistent 3D Geometry
  ☆319Updated last month
• QitaoZhao / DiffusionSfM
  [CVPR 2025] "DiffusionSfM: Predicting Structure and Motion via Ray Origin and Endpoint Diffusion" official implementation.
  ☆174Updated 4 months ago
• NVlabs / LSM
  [NeurIPS'24] Large Spatial Model: End-to-end Unposed Images to Semantic 3D
  ☆221Updated 2 weeks ago
• LiteReality / LiteReality
  LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans
  ☆285Updated 4 months ago
• aharley / alltracker
  AllTracker is a model for tracking all pixels in a video.
  ☆365Updated 2 months ago
• Inception3D / TTT3R
  A simple state update rule to enhance length generalization for CUT3R
  ☆504Updated last month
• NIRVANALAN / STream3R
  Dynamic 3D Foundation Model using Causal Transformer
  ☆279Updated last month
• Stereo4d / stereo4d-code
  Stereo4D dataset and processing code
  ☆273Updated last week
• facebookresearch / mvdust3r
  Open source impl of **MV-DUSt3R+ Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds** from Meta Reality Labs. Project page …
  ☆548Updated last week
• florinshen / FlashSplat
  [ECCV2024] [3DV Nectar 2025] FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally
  ☆237Updated last year
• hujiecpp / PE3R
  PE3R: Perception-Efficient 3D Reconstruction. Take 2 - 3 photos with your phone, upload them, wait a few minutes, and then start explorin…
  ☆390Updated 7 months ago
• VITA-Group / VideoLifter
  Official implementation of "VideoLifter: Lifting Videos to 3D with Fast Hierarchical Stereo Alignment"
  ☆136Updated 9 months ago
• Davidyao99 / uni4d
  [CVPR 2025] Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video
  ☆200Updated 5 months ago
• kai422 / DAS3R
  DAS3R: Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction
  ☆145Updated 8 months ago
• Anttwo / MAtCha
  [CVPR 2025 - Spotlight] Official PyTorch implementation of MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism F…
  ☆243Updated 7 months ago
• ibaiGorordo / vggt-pytorch-inference
  Repository for running the VGGT model in PyTorch
  ☆167Updated 6 months ago
• NVlabs / GaussianSTORM
  [ICLR2025] A PyTorch implementation for STORM: Spatiotemporal Reconstruction Model for Large-Scale Outdoor Scenes
  ☆270Updated 5 months ago
• KevinXu02 / splatfacto-w
  ☆120Updated last year
• albert100121 / Depth-Anywhere
  ☆95Updated 4 months ago