Hugging Face's logo

KevinMathew
/
dynadust3r-unofficial-weights

Model card Files
xet
Community

DynaDUSt3R (Unofficial) — Model Weights

This repository hosts PyTorch .pth checkpoint files for the DynaDUSt3R model — an external, unofficial reimplementation of the model proposed in the paper Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos by Linyi Jin, Richard Tucker, Zhengqi Li, David Fouhey, Noah Snavely, and Aleksander Hołyński.

Overview

DynaDUSt3R extends DUSt3R to dynamic scenes by predicting per-pixel 3D points and 3D motion trajectories from stereo video sequences.
These weights were obtained from an independent reimplementation and are provided solely for research and reproducibility purposes.

The accompanying codebase can be found in the dynadust3r-unofficial repository.
Instructions for running inference are available in the inference example script.

Contents

  • .pth checkpoint files corresponding to trained DynaDUSt3R models.
  • Optional SHA256SUMS.txt for integrity verification.

These checkpoints are compatible with the model definitions in the dynadust3r-unofficial repository.

Usage

Please follow the setup and inference steps described in the main dynadust3r-unofficial repository.
The weights can be loaded using torch.load() as shown in the inference example.

Note: .pth files use Python pickle and should only be loaded from trusted sources.

ADT Evaluation — motion_left_weighted

The table below summarizes motion_left_weighted metrics extracted from evaluation logs using regex.
All runs used num_pairs = 80. Lower EPE3D is better; higher δ3D@0.05m / δ3D@0.10m are better.
Sorting: by EPE3D (ascending).

Checkpoint Loss EPE3D δ3D@0.05m δ3D@0.10m
best_loss_0.480798_iter_90000_epoch_45.pth 0.480798 0.097590 0.579054 0.721840
best_loss_0.499884_iter_26000_epoch_13.pth 0.499884 0.099967 0.584089 0.702858
best_loss_0.367080_iter_34000_epoch_17.pth 0.367080 0.107291 0.584089 0.692632
best_loss_0.386052_iter_38000_epoch_19.pth 0.386052 0.110886 0.578398 0.689224
best_loss_0.493017_iter_66000_epoch_33.pth 0.493017 0.113498 0.609419 0.709300
best_loss_0.525647_iter_28000_epoch_14.pth 0.525647 0.114329 0.593752 0.685002
best_loss_0.480609_iter_40000_epoch_20.pth 0.480609 0.114391 0.593533 0.696479
best_loss_0.468565_iter_58000_epoch_29.pth 0.468565 0.115336 0.602633 0.695728
best_loss_0.443512_iter_88000_epoch_44.pth 0.443512 0.116817 0.581650 0.699418
best_loss_0.427857_iter_92000_epoch_46.pth 0.427857 0.116859 0.562699 0.680437
best_loss_0.392713_iter_94000_epoch_47.pth 0.392713 0.117412 0.559729 0.689130
best_loss_0.523247_iter_42000_epoch_21.pth 0.523247 0.118066 0.558916 0.670836
best_loss_0.503958_iter_82000_epoch_41.pth 0.503958 0.119068 0.569016 0.672775
best_loss_0.396031_iter_32000_epoch_16.pth 0.396031 0.119268 0.576302 0.686316
best_loss_0.528999_iter_60000_epoch_30.pth 0.528999 0.119764 0.605854 0.693508
best_loss_0.482799_iter_86000_epoch_43.pth 0.482799 0.122681 0.592657 0.691256
last_iter_98000_epoch_49.pth 0.123712 0.583620 0.689787
best_loss_0.427555_iter_24000_epoch_12.pth 0.427555 0.125248 0.574051 0.672212
best_loss_0.527959_iter_30000_epoch_15.pth 0.527959 0.125830 0.596410 0.689818
best_loss_0.478208_iter_56000_epoch_28.pth 0.478208 0.126261 0.597286 0.691444
best_loss_0.431392_iter_52000_epoch_26.pth 0.431392 0.126944 0.573175 0.691069

References

License

These weights are provided for research and non-commercial use only.
This repository is unofficial and not affiliated with the authors of Stereo4D.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support