Search Results for author: Tianxiang Ma

Found 11 papers, 2 papers with code

Phantom: Subject-consistent video generation via cross-modal alignment

no code implementations16 Feb 2025 Lijie Liu, Tianxiang Ma, Bingchuan Li, Zhuowei Chen, Jiawei Liu, Qian He, Xinglong Wu

The continuous development of foundational models for video generation is evolving into various applications, with subject-consistent video generation still in the exploratory stage.

cross-modal alignment Triplet +1

I2VControl: Disentangled and Unified Video Motion Synthesis Control

no code implementations26 Nov 2024 Wanquan Feng, Tianhao Qi, Jiawei Liu, Mingzhen Sun, Pengqi Tu, Tianxiang Ma, Fei Dai, Songtao Zhao, Siyu Zhou, Qian He

Video synthesis techniques are undergoing rapid progress, with controllability being a significant aspect of practical usability for end-users.

Motion Synthesis

I2VControl-Camera: Precise Video Camera Control with Adjustable Motion Strength

no code implementations10 Nov 2024 Wanquan Feng, Jiawei Liu, Pengqi Tu, Tianhao Qi, Mingzhen Sun, Tianxiang Ma, Songtao Zhao, Siyu Zhou, Qian He

To accurately control and adjust the strength of subject motion, we explicitly model the higher-order components of the video trajectory expansion, not merely the linear terms, and design an operator that effectively represents the motion strength.

Video Generation

RS-Corrector: Correcting the Racial Stereotypes in Latent Diffusion Models

no code implementations8 Dec 2023 Yue Jiang, Yueming Lyu, Tianxiang Ma, Bo Peng, Jing Dong

Extensive empirical evaluations demonstrate that the introduced \themodel effectively corrects the racial stereotypes of the well-trained Stable Diffusion model while leaving the original model unchanged.

Image Generation

GaFET: Learning Geometry-aware Facial Expression Translation from In-The-Wild Images

no code implementations ICCV 2023 Tianxiang Ma, Bingchuan Li, Qian He, Jing Dong, Tieniu Tan

In this paper, we introduce a novel Geometry-aware Facial Expression Translation (GaFET) framework, which is based on parametric 3D facial representations and can stably decoupled expression.

Facial Expression Translation

Freestyle 3D-Aware Portrait Synthesis Based on Compositional Generative Priors

no code implementations27 Jun 2023 Tianxiang Ma, Kang Zhao, Jianxin Sun, Yingya Zhang, Jing Dong

Efficiently generating a freestyle 3D portrait with high quality and 3D-consistency is a promising yet challenging task.

CFFT-GAN: Cross-domain Feature Fusion Transformer for Exemplar-based Image Translation

no code implementations3 Feb 2023 Tianxiang Ma, Bingchuan Li, Wei Liu, Miao Hua, Jing Dong, Tieniu Tan

In this paper, we propose a more general learning approach by considering two domain features as a whole and learning both inter-domain correspondence and intra-domain potential information interactions.

Translation

Semantic 3D-aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Field

1 code implementation3 Feb 2023 Tianxiang Ma, Bingchuan Li, Qian He, Jing Dong, Tieniu Tan

CNeRF divides the image by semantic regions and learns an independent neural radiance field for each region, and finally fuses them and renders the complete image.

NeRF

ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing

no code implementations31 Jan 2023 Bingchuan Li, Tianxiang Ma, Peng Zhang, Miao Hua, Wei Liu, Qian He, Zili Yi

Specifically, in Phase I, a W-space-oriented StyleGAN inversion network is trained and used to perform image inversion and editing, which assures the editability but sacrifices reconstruction quality.

Image Generation

CFA-Net: Controllable Face Anonymization Network with Identity Representation Manipulation

no code implementations24 May 2021 Tianxiang Ma, Dongze Li, Wei Wang, Jing Dong

We propose a Controllable Face Anonymization Network (CFA-Net), a novel approach that can anonymize the identity of given faces in images and videos, based on a generator that can disentangle face identity from other image contents.

De-identification Face Anonymization

MUST-GAN: Multi-level Statistics Transfer for Self-driven Person Image Generation

1 code implementation CVPR 2021 Tianxiang Ma, Bo Peng, Wei Wang, Jing Dong

To deal with this problem, we propose a novel multi-level statistics transfer model, which disentangles and transfers multi-level appearance features from person images and merges them with pose features to reconstruct the source person images themselves.

Pose Transfer Style Transfer

Cannot find the paper you are looking for? You can Submit a new open access paper.