Papers with Code · CC BY-SA 4.0

Lifelike 3D Human Generation

6 평가 기록 1 datasets

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.

논문

Human-VDM: Learning Single-Image 3D Human Gaussian Splatting from Video Diffusion Models

2409.02851 2024-09-04 이 페이지의 평가 1건

CLIP Similarity: 0.9235SSIM: 0.9228LPIPS: 0.0957PSNR: 20.068

PaMIR: Parametric Model-Conditioned Implicit Representation for Image-based Human Reconstruction

2007.03858 2020-07-08 이 페이지의 평가 1건

CLIP Similarity: 0.8861SSIM: 0.8924LPIPS: 0.1461PSNR: 16.6267

PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization

1905.05172 2019-05-13 이 페이지의 평가 1건

CLIP Similarity: 0.8501SSIM: 0.8884LPIPS: 0.1615PSNR: 15.0248

SIFU: Side-view Conditioned Implicit Function for Real-world Usable Clothed Human Reconstruction

2312.06704 2023-12-10 이 페이지의 평가 1건

CLIP Similarity: 0.8663SSIM: 0.7931LPIPS: 0.1500PSNR: 16.4600

SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion

2311.15855 2023-11-27 이 페이지의 평가 1건

CLIP Similarity: 0.8978SSIM: 0.8963LPIPS: 0.1396PSNR: 17.0533

Ultraman: Single Image 3D Human Reconstruction with Ultra Speed and Detail

2403.12028 2024-03-18 이 페이지의 평가 1건

CLIP Similarity: 0.9131SSIM: 0.8958LPIPS: 0.1338PSNR: 17.4877