SMPL AMC Imitator

For a given AMC/ASF motion sequence, we transfer the motion to SMPL model, and generate a corresponding 3D SMPL sequence. GitHub link: SMPL-AMC-Imitator.

This work is based on my implmentation of SMPL model and my implementation of AMC/ASF parser.

Demo

Skeleton (left: SMPL target, right: ASF/AMC source)

Skeleton Demo

Skinned Model

Skinned Demo

Usage

Quick Demo

Run python 3Dviewer.py to see demo.

Also, run python batch.py to extract all poses into ./pose/ from ./data/.

Step by Step Tutorial

  1. Use reader.parse_asf() to extract skeleton definition from .asf file: joints = reader.parse_asf(asf_path)

  2. Use reader.parse_amc() to extract motion sequence from .amc file: motions = reader.parse_amc(amc_path)

  3. Construct a smpl_np.SMPLModel object: smpl = SMPLModel(smpl_model_path)

  4. Construct a imitator.Imitator object: imit = Imitator(joints, smpl)

  5. Use imitator.Imitator.imitate to manipulate SMPL model to some pose: imit.imitate(motions[frame_index])

  6. Use smpl_np.output_mesh to get .obj file: imit.smpl.output_mesh(output_path)

In step 5, the SMPLModel inside Imitator is set to the same pose as motions[frame_idx].

For any questions, feel free to open an issue.

Challenge

The skeleton of SMPL is a little bit different from CMU MoCap Dataset’s. In this implementation, we only process femur and tibia and ignore other differences. We first pose SMPL skeleton (specifically legs) to be in the same pose with ASF defination. After that, we extract rotation matrices from AMC files and apply them to the aligned SMPL model.

Feel free to contact me for more details.