https://github.com/3dtopia/3dtopia
공식 코드3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
The fundamental goal of example-based Texture Synthesis is to generate a texture, usually larger than the input, that faithfully captures all the visual characteristics of the exemplar, yet is neither identical to it, nor exhibits obvious unnatural looking artifacts.
Source: Non-Stationary Texture Synthesis by Adversarial Expansion
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors
DeFLOCNet: Deep Image Editing via Flexible Low-level Controls
Generic 3D Diffusion Adapter Using Controlled Multi-View Editing
HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts
StructureFlow: Image Inpainting via Structure-aware Appearance Flow
Keys to Better Image Inpainting: Structure and Texture Go Hand in Hand
Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE
Tex4D: Zero-shot 4D Scene Texturing with Video Diffusion Models
Generalized Rectifier Wavelet Covariance Models For Texture Synthesis
TexTailor: Customized Text-aligned Texturing via Effective Resampling
Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering
Local Padding in Patch-Based GANs for Seamless Infinite-Sized Texture Synthesis
Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks
GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture Details
Conceptual Compression via Deep Structure and Texture Synthesis
Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors
Iterative Token Evaluation and Refinement for Real-World Super-Resolution
Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors
Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis
Precomputed Real-Time Texture Synthesis with Markovian Generative Adversarial Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.