Wish You Were Here: Context-Aware Human Generation
원문 초록
We present a novel method for inserting objects, specifically humans, into existing images, such that they blend in a photorealistic manner, while respecting the semantic context of the scene. Our method involves three subnetworks: the first generates the semantic map of the new person, given the pose of the other persons in the scene and an optional bounding box specification. The second network renders the pixels of the novel person and its blending mask, based on specifications in the form of multiple appearance components. A third network refines the generated face in order to match those of the target person. Our experiments present convincing high-resolution outputs in this novel and challenging application domain. In addition, the three networks are evaluated individually, demonstrating for example, state of the art results in pose transfer benchmarks.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Learning Flow Fields in Attention for Controllable Person Image Generation
TryOffDiff: Virtual-Try-Off via High-Fidelity Garment Reconstruction using Diffusion Models
One-Shot Learning for Pose-Guided Person Image Synthesis in the Wild
Weakly-supervised 3D Pose Transfer with Keypoints
Bidirectionally Deformable Motion Modulation For Video-based Human Pose Transfer
DSFFNet: Dual-Side Feature Fusion Network for 3D Pose Transfer
토론
이 논문과 연결된 포럼 글이 아직 없습니다.