Style Transfer
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 6
- 평가표
- 5
- 보존된 평가 기록
- 12
Style Transfer is a technique in computer vision and graphics that involves generating a new image by combining the content of one image with the style of another image. The goal of style transfer is to create an image that preserves the content of the original image while applying the visual style of another image.
<span style="color:grey; opacity: 0.6">( Image credit: A Neural Algorithm of Artistic Style )</span>
- "T" as a sofa:
The "T" horizontal strip can mimic the back of a sofa with a delicate cushion or details of the uphols or appliances with the color button.
The "T" vertical strip can show a feet or arm of the sofa, shiny, yet firm.
- Merge "P":
Put "P" next to "T", your curve to delicately with the top "T." It is intertwined. The circular part of "P" can show a cushion or a curved chair and synchronize the subject of furniture.
Make sure "P" is visually relying on "T", which reflects the relationship of cohesion and balance.
- Coherence of "B" and "I":
"B" can be aligned as a pair of cushions or a modern chair, with mild curves with glossy and modern aesthetics.
"I" can be a symbol of a shiny furniture or a vertical light bar and completes the shapes without overburdess them.
Color palette 4:
Includes soft soil colors such as beige, top and gray shades, along with silent or silver gold tips to touch elegance.
Consider a slope effect to enhance modernity, to keep colors elegant and complex.
- Connect the letters:
Use the overlap or intertwined edges that the letters meet for the symbol of unity.
The plan should allow viewers to distinguish each letter while feeling part of the same "structure".
- Background patterns:
Use delicate geometric patterns or textures that mimic fabrics or furniture materials such as wood seeds or woven fibers.
These patterns must remain minimalist and focus on highlighting the logo, while maintaining communication.
While it deals with the subject of furniture and design, this concept conveys modernity, creativity and professional. If you like, I can create a draft design for better visualization.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/jakezhaojb/ARAE
공식 코드https://github.com/jamie-cheung/artbank
공식 코드ArtBank: Artistic Style Transfer with Pre-trained Diffusion Model and Implicit Style Prompt Bank
https://github.com/jamie-cheung/lsast
공식 코드https://github.com/jankowskichristopher/red-teaming-segment-anything-model
공식 코드https://github.com/jarek-pawlowski/microbial-dataset-generation
공식 코드Generation of microbial colonies dataset with deep learning style transfer
https://github.com/jayoungkim408/sos
공식 코드https://github.com/jayparanjape/f-vita
공식 코드F-ViTA: Foundation Model Guided Visible to Thermal Translation
https://github.com/jcyang98/inst
공식 코드Industrial Style Transfer with Large-scale Geometric Warping and Content Preservation
https://github.com/jeremyxsc/finegpr
공식 코드Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identification
https://github.com/jhtonykoo/music_mixing_style_transfer
공식 코드Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects
https://github.com/jiashunwang/Neural-Pose-Transfer
공식 코드Neural Pose Transfer by Spatially Adaptive Instance Normalization
https://github.com/jiechen2358/VirtualFittingRoom
공식 코드https://github.com/jiwoogit/StyleID
공식 코드https://github.com/johannwyh/styleinv
공식 코드StyleInV: A Temporal Style Modulated Inversion Network for Unconditional Video Generation
https://github.com/josephcao0327/stylefool
공식 코드StyleFool: Fooling Video Classification Systems via Style Transfer
https://github.com/judydnguyen/pardon-feddg
공식 코드PARDON: Privacy-Aware and Robust Federated Domain Generalization
https://github.com/junhocho/paired-glyph-matching
공식 코드https://github.com/junleen/RainNet
공식 코드Region-aware Adaptive Instance Normalization for Image Harmonization
https://github.com/junyanz/CycleGAN
공식 코드Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix
공식 코드Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks
https://github.com/juseonghan/meshbrush
공식 코드MeshBrush: Painting the Anatomical Mesh with Neural Stylization for Endoscopy
https://github.com/jwen307/diamondintherough
공식 코드Diamond in the rough: Improving image realism by traversing the GAN latent space
https://github.com/kartikeypant/text-simplification-qa-www2021
공식 코드Text Simplification for Comprehension-based Question-Answering
https://github.com/katieluo88/staypositive
공식 코드Stay Positive: Non-Negative Image Synthesis for Augmented Reality
https://github.com/kedz/styleeq
공식 코드Low-Level Linguistic Controls for Style Transfer and Content Preservation
https://github.com/keithecarlson/StyleTransferBibleData
공식 코드https://github.com/kent0n-li/samscore
공식 코드SAMScore: A Content Structural Similarity Metric for Image Translation Evaluation
https://github.com/keonlee9420/STYLER
공식 코드https://github.com/keshavbhandari/improvnet
공식 코드ImprovNet -- Generating Controllable Musical Improvisations with Iterative Corruption Refinement
https://github.com/khainb/quasi-sw
공식 코드https://github.com/kibeom-hong/aespa-net
공식 코드https://github.com/kibeom-hong/domain-aware-style-transfer
공식 코드https://github.com/kikyo-16/coco-mulla-repo
공식 코드https://github.com/kingjamessong/fastdifferentiablematsqrt
공식 코드Fast Differentiable Matrix Square Root and Inverse Square Root
https://github.com/kornelhowil/clipgaussian
공식 코드CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.