Pose Transfer

41 papers with code • 6 benchmarks • 5 datasets

This task has no description! Would you like to contribute one?

Weakly-supervised 3D Pose Transfer with Keypoints

jinnan-chen/3d-pose-transfer ICCV 2023

The main challenges of 3D pose transfer are: 1) Lack of paired training data with different characters performing the same pose; 2) Disentangling pose and shape information from the target mesh; 3) Difficulty in applying to meshes with different topologies.

4
25 Jul 2023

Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer

rocketappslab/bdmm ICCV 2023

To address these issues, we propose a novel Deformable Motion Modulation (DMM) that utilizes geometric kernel offset with adaptive weight modulation to simultaneously perform feature alignment and style transfer.

46
15 Jul 2023

Zero-shot Pose Transfer for Unrigged Stylized 3D Characters

jiashunwang/ZPT CVPR 2023

We present a zero-shot approach that requires only the widely available deformed non-stylized avatars in training, and deforms stylized characters of significantly different shapes at inference.

10
31 May 2023

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

justin941208/mapconnet ICCV 2023

Unsupervised methods have been proposed for graph convolutional models but they require ground truth correspondence between the source and target inputs.

6
26 Apr 2023

UPGPT: Universal Diffusion Model for Person Image Generation, Editing and Pose Transfer

soon-yau/upgpt 18 Apr 2023

Text-to-image models (T2I) such as StableDiffusion have been used to generate high quality images of people.

94
18 Apr 2023

Composer: Creative and Controllable Image Synthesis with Composable Conditions

modelscope/modelscope 20 Feb 2023

Recent large-scale generative models learned on big data are capable of synthesizing incredible images yet suffer from limited controllability.

5,888
20 Feb 2023

Unsupervised 3D Pose Transfer with Cross Consistency and Dual Reconstruction

ChaoyueSong/X-DualNet 18 Nov 2022

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.

18
18 Nov 2022

SCAM! Transferring humans between images with Semantic Cross Attention Modulation

nicolas-dufour/SCAM 10 Oct 2022

In this work, we introduce SCAM (Semantic Cross Attention Modulation), a system that encodes rich and diverse information in each semantic region of the image (including foreground and background), thus achieving precise generation with emphasis on fine details.

54
10 Oct 2022

Collecting The Puzzle Pieces: Disentangled Self-Driven Human Pose Transfer by Permuting Textures

nannanli999/pt_square ICCV 2023

Then we reconstruct the input image by sampling from the permuted textures for patch-level disentanglement.

1
04 Oct 2022

Cross Attention Based Style Distribution for Controllable Person Image Synthesis

xyzhouo/casd 1 Aug 2022

In this paper, we propose a cross attention based style distribution module that computes between the source semantic styles and target pose for pose transfer.

58
01 Aug 2022