Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction

by   Chaoyue Song, et al.

The goal of 3D pose transfer is to transfer the pose from the source mesh to the target mesh while preserving the identity information (e.g., face, body shape) of the target mesh. Deep learning-based methods improved the efficiency and performance of 3D pose transfer. However, most of them are trained under the supervision of the ground truth, whose availability is limited in real-world scenarios. In this work, we present X-DualNet, a simple yet effective approach that enables unsupervised 3D pose transfer. In X-DualNet, we introduce a generator G which contains correspondence learning and pose transfer modules to achieve 3D pose transfer. We learn the shape correspondence by solving an optimal transport problem without any key point annotations and generate high-quality meshes with our elastic instance normalization (ElaIN) in the pose transfer module. With G as the basic component, we propose a cross consistency learning scheme and a dual reconstruction objective to learn the pose transfer without supervision. Besides that, we also adopt an as-rigid-as-possible deformer in the training process to fine-tune the body shape of the generated results. Extensive experiments on human and animal data demonstrate that our framework can successfully achieve comparable performance as the state-of-the-art supervised approaches.


page 8

page 10

page 16

page 17

page 18

page 19

page 21

page 22


3D Pose Transfer with Correspondence Learning and Mesh Refinement

3D pose transfer is one of the most challenging 3D generation tasks. It ...

MAPConNet: Self-supervised 3D Pose Transfer with Mesh and Point Contrastive Learning

3D pose transfer is a challenging generation task that aims to transfer ...

Unsupervised Shape and Pose Disentanglement for 3D Meshes

Parametric models of humans, faces, hands and animals have been widely u...

Can Action be Imitated? Learn to Reconstruct and Transfer Human Dynamics from Videos

Given a video demonstration, can we imitate the action contained in this...

Weakly-supervised 3D Pose Transfer with Keypoints

The main challenges of 3D pose transfer are: 1) Lack of paired training ...

Dual-Side Feature Fusion 3D Pose Transfer

3D pose transfer solves the problem of additional input and corresponden...

Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer

With the strength of deep generative models, 3D pose transfer regains in...

Please sign up or login with your details

Forgot password? Click here to reset