Animate anyone: Consistent and controllable image-to-video synthesis for character animation
L Hu - Proceedings of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Character Animation aims to generating character videos from still images through driving
signals. Currently diffusion models have become the mainstream in visual generation …
signals. Currently diffusion models have become the mainstream in visual generation …
Person image synthesis via denoising diffusion model
The pose-guided person image generation task requires synthesizing photorealistic images
of humans in arbitrary poses. The existing approaches use generative adversarial networks …
of humans in arbitrary poses. The existing approaches use generative adversarial networks …
Humansd: A native skeleton-guided diffusion model for human image generation
Controllable human image generation (HIG) has attracted significant attention from
academia and industry for its numerous real-life applications. State-of-the-art solutions, such …
academia and industry for its numerous real-life applications. State-of-the-art solutions, such …
Bidirectionally deformable motion modulation for video-based human pose transfer
Video-based human pose transfer is a video-to-video generation task that animates a plain
source human image based on a series of target human poses. Considering the difficulties …
source human image based on a series of target human poses. Considering the difficulties …
Appearance and Pose-guided Human Generation: A Survey
F Liao, X Zou, W Wong - ACM Computing Surveys, 2024 - dl.acm.org
Appearance and pose-guided human generation is a burgeoning field that has captured
significant attention. This subject's primary objective is to transfer pose information from a …
significant attention. This subject's primary objective is to transfer pose information from a …
Controllable person image synthesis with pose-constrained latent diffusion
Controllable person image synthesis aims at rendering a source image based on user-
specified changes in body pose or appearance. Prior art approaches leverage pixel-level …
specified changes in body pose or appearance. Prior art approaches leverage pixel-level …
Unitedhuman: Harnessing multi-source data for high-resolution human generation
Human generation has achieved significant progress. Nonetheless, existing methods still
struggle to synthesize specific regions such as faces and hands. We argue that the main …
struggle to synthesize specific regions such as faces and hands. We argue that the main …
Learning disentangled identifiers for action-customized text-to-image generation
This study focuses on a novel task in text-to-image (T2I) generation namely action
customization. The objective of this task is to learn the co-existing action from limited data …
customization. The objective of this task is to learn the co-existing action from limited data …
Coarse-to-fine latent diffusion for pose-guided person image synthesis
Diffusion model is a promising approach to image generation and has been employed for
Pose-Guided Person Image Synthesis (PGPIS) with competitive performance. While existing …
Pose-Guided Person Image Synthesis (PGPIS) with competitive performance. While existing …
Advancing pose-guided image synthesis with progressive conditional diffusion models
Recent work has showcased the significant potential of diffusion models in pose-guided
person image synthesis. However, owing to the inconsistency in pose between the source …
person image synthesis. However, owing to the inconsistency in pose between the source …