Author: Hao Tang;
Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis
Deep Unsupervised Key Frame Extraction for Eficient Video Classification
Bipartite Graph Reasoning GANs for Person Pose and Facial Image Synthesis
Local and Global GANs with Semantic-Aware Upsampling for Image Generation
AttentionGAN: Unpaired Image-to-Image Translation Using Attention-Guided Generative Adversarial Networks
Total Generate: Cycle in Cycle Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes
When Dictionary Learning Meets Deep Learning: Deep Dictionary Learning and Coding Network for Image Recognition With Limited Data
Disentangle Saliency Detection into Cascaded Detail Modeling and Body Filling
Quasi-equilibrium Feature Pyramid Network for Salient Object Detection
3D-Aware Semantic-Guided Generative Model for Human Synthesis
Unsupervised High-Resolution Portrait Gaze Correction and Animation
Geometry-Contrastive Transformer for Generalized 3D Pose Transfer
Intrinsic-Extrinsic Preserved GANs for Unsupervised 3D Pose Transfer
Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction
AniFormer: Data-driven 3D Animation with Transformer
We present a novel task, i.e., animating a target 3D object through the motion of a raw driving sequence. In previous works, extra auxiliary correlations between source and target meshes or intermedia factors are inevitable to capture the motions in the driving sequences. Instead, we introduce AniFormer, a novel Transformer-based architecture, that generates animated 3D sequences by directly taking the raw driving sequences and arbitrary same-type target meshes as inputs. Specifically, we customize the Transformer architecture for 3D animation that generates mesh sequences by integrating styles from target meshes and motions from the driving meshes. Besides, instead of the conventional single regression head in the vanilla Transformer, AniFormer generates multiple frames as outputs to preserve the sequential consistency of the generated meshes. To achieve this, we carefully design a pair of regression constraints, i.e., motion and appearance constraints, that can provide strong regularization on the generated mesh sequences. Our AniFormer achieves high-fidelity, realistic, temporally coherent animated results and outperforms compared start-of-the-art methods on benchmarks of diverse categories. Code is available: https://github.com/mikecheninoulu/AniFormer.