Awesome

Im2Hands (Implicit Two Hands)

Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes (CVPR 2023)

Jihyun Lee, Minhyuk Sung, Honggyu Choi, Tae-Kyun (T-K) Kim

[Project Page] [Paper] [Supplementary Video]

CVPR 2023 Materials: [Presentation Video] <a href="https://jyunlee.github.io/projects/implicit-two-hands/data/cvpr2023_poster.pdf" class="image fit" type="application/pdf">[Poster]</a>

We present Implicit Two Hands (Im2Hands), the first neural implicit representation of two interacting hands. Unlike existing methods on two-hand reconstruction that rely on a parametric hand model and/or low-resolution meshes, Im2Hands can produce fine-grained geometry of two hands with high hand-to-hand and hand-to-image coherency. To handle the shape complexity and interaction context between two hands, Im2Hands models the occupancy volume of two hands - conditioned on an RGB image and coarse 3D keypoints - by two novel attention-based modules responsible for initial occupancy estimation and context-aware occupancy refinement, respectively. Im2Hands first learns per-hand neural articulated occupancy in the canonical space designed for each hand using query-image attention. It then refines the initial two-hand occupancy in the posed space to enhance the coherency between the two hand shapes using query-anchor attention. In addition, we introduce an optional keypoint refinement module to enable robust two-hand shape estimation from predicted hand keypoints in a single-image reconstruction scenario. We experimentally demonstrate the effectiveness of Im2Hands on two-hand reconstruction in comparison to related methods, where ours achieves state-of-the-art results.

Environment Setup

Clone this repository and install the dependencies specified in requirements.txt.

Also, install im2mesh library of Occupancy Networks.

Data Preparation

1. Download InterHand2.6M dataset from its official website. Set the value of path variable in your config file as the path of annotation directory of InterHand2.6M.
2. Follow the data pre-processing steps of HALO for sampling query points and the corresponding ground truth occupancy values. For modifying prepare_data_from_mano_param_keypoints.py file of HALO for InterHand2.6M dataset, you can refer to this file. (Sorry that this code is currently a bit messy; I will try to refactor it when I have more time.)
3. Follow the data pre-processing steps of IntagHand (dataset/interhand.py) to obtain normalized two-hand images. Set the value of img_path variable in your config file as the path of the resulting data directory.
4. Place your hand keypoint files - either the ground truth keypoints of InterHand2.6M or predicted keypoints extracted using e.g. IntagHand - under pred_joints sub-directory under your pre-processed data directory.

Initial Occupancy Estimation Network

Network Training

Place the pre-trained weights of HALO and IntagHand (halo_baseline.pt and intaghand_baseline.pth) under out/init_occ directory. These files can be also downloaded from this Google Drive link.

Then, Run init_occ_train.py to train your own Initial Occupancy Estimation Network.

Network Inference

Run init_occ_generate.py to generate the initial per-hand shapes.

Two-Hand Occupancy Refinement Network

Network Training

Place the weights of Initial Occupancy Estimation Network (init_occ.pt) under out/ref_occ directory. The pre-trained weights can be also downloaded from this Google Drive link.

Then, run ref_occ_train.py to train your own Refined Occupancy Estimation Network.

For quantitative evaluation, please refer to eval_meshes.py script of HALO.

Network Inference

Run ref_occ_generate.py to generate the refined two-hand shapes.

[Optional] Keypoint Refinement Network

Network Training

Place the pre-trained weights of IntagHand (intaghand_baseline.pth) under out/kpts_ref directory. This file can be also downloaded from this Google Drive link.

Also, place (1) your initial hand keypoint files (e.g. predicted using IntagHand) under pred_joints_before_ref sub-directory and (2) the ground truth keypoints of InterHand2.6M under gt_joints sub-directory of your pre-processed data directory.

Then, Run kpts_ref_train.py to train your own Input Keypoint Refinement Network.

Network Inference

Run kpts_ref_generate.py to save the refined two-hand keypoints.

For quantitative evaluation, please refer to apps/eval_interhand.py script of IntagHand.

Citation

If you find this work useful, please consider citing our paper.

@InProceedings{lee2023im2hands,
    author = {Lee, Jihyun and Sung, Minhyuk and Choi, Honggyu and Kim, Tae-Kyun},
    title = {Im2Hands: Learning Attentive Implicit Representation of Interacting Two-Hand Shapes},
    booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year = {2023}
}

Acknowledgements

• Our code is based on HALO, IntagHand, and AIR-Nets, and our model parameters are partially initialized from their pre-trained weights. We thank the authors of these three inspiring works.
• We also thank the authors of InterHand2.6M for the useful dataset.