CGANs Based User Preferred Photorealistic Re-stylization of Social Image

Li, Zhen; Yuan, Meng; Nie, Jie; Huang, Lei; Wei, Zhiqiang

doi:10.1007/978-3-030-00767-6_13

Cited by 1 publication

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There has been a recent surge of interest in the field of generating 3D shapes and textures. One line of methods, such as Text2Mesh (Michel et al 2022), Tango (Lei et al 2022), and CLIP-Mesh (Mohammad Khalid et al 2022), utilize CLIP-space similarities as an optimization objective to create novel 3D shapes and textures. Gao et al (2022) trains a model to generate shape and texture via a DMTet (Shen et al 2021) mesh extractor and 2D adversarial losses.…”

Section: Introductionmentioning

confidence: 99%

PaintHuman: Towards High-Fidelity Text-to-3D Human Texturing via Denoised Score Distillation

Yu,

Zhu,

Jiang

et al. 2024

AAAI

View full text Add to dashboard Cite

Recent advances in zero-shot text-to-3D human generation, which employ the human model prior (e.g., SMPL) or Score Distillation Sampling (SDS) with pre-trained text-to-image diffusion models, have been groundbreaking. However, SDS may provide inaccurate gradient directions under the weak diffusion guidance, as it tends to produce over-smoothed results and generate body textures that are inconsistent with the detailed mesh geometry. Therefore, directly leveraging existing strategies for high-fidelity text-to-3D human texturing is challenging. In this work, we propose a model called PaintHuman to addresses the challenges from two perspectives. We first propose a novel score function, Denoised Score Distillation (DSD), which directly modifies the SDS by introducing negative gradient components to iteratively correct the gradient direction and generate high-quality textures. In addition, we use the depth map as a geometric guide to ensure that the texture is semantically aligned to human mesh surfaces. To guarantee the quality of rendered results, we employ geometry-aware networks to predict surface materials and render realistic human textures. Extensive experiments, benchmarked against state-of-the-art (SoTA) methods, validate the efficacy of our approach.Project page: https://painthuman.github.io/.

show abstract

Section: Introductionmentioning

confidence: 99%