https://github.com/Human-VDM/Human-VDM
공식 코드Human-VDM: Learning Single-Image 3D Human Gaussian Splatting from Video Diffusion Models
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Generating realistic and lifelike 3D Humans from a Single RGB image input, while preserving face identity, delivering realistic texture, accurate geometry, and maintaining a valid pose of the generated human.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Human-VDM: Learning Single-Image 3D Human Gaussian Splatting from Video Diffusion Models
SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction
SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion
PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction
Ultraman: Single Image 3D Human Reconstruction with Ultra Speed and Detail
PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.