Imagen de Portada

Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Kim, Hyunsoo, Kim, Donghyun, Kim, Suhyun
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

When Model Knowledge meets Diffusion Model: Diffusion-assisted Data-free Image Synthesis with Alignment of Domain and Class
por: Kim, Yujin, et al.
Publicado: (2025)

Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted Adaptation
por: Kim, Yongwoo, et al.
Publicado: (2026)

Probabilistic Precision and Recall Towards Reliable Evaluation of Generative Models
por: Park, Dogyun, et al.
Publicado: (2023)

Crafting Query-Aware Selective Attention for Single Image Super-Resolution
por: Kim, Junyoung, et al.
Publicado: (2025)

Durian: Dual Reference Image-Guided Portrait Animation with Attribute Transfer
por: Cha, Hyunsoo, et al.
Publicado: (2025)

Comparison Reveals Commonality: Customized Image Generation through Contrastive Inversion
por: Kim, Minseo, et al.
Publicado: (2025)

Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation
por: Kim, Jihyun, et al.
Publicado: (2024)

PEGASUS: Personalized Generative 3D Avatars with Composable Attributes
por: Cha, Hyunsoo, et al.
Publicado: (2024)

Language-Grounded Multi-Domain Image Translation via Semantic Difference Guidance
por: Ryu, Jongwon, et al.
Publicado: (2026)

A More Word-like Image Tokenization for MLLMs
por: Lee, Hyun, et al.
Publicado: (2026)

Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation
por: Kim, Beomyoung, et al.
Publicado: (2024)

FALCON: Frequency Adjoint Link with CONtinuous Density Mask for Fast Single Image Dehazing
por: Kim, Donghyun, et al.
Publicado: (2024)

Structured State-Space Regularization for Generation-Friendly Image Tokenization
por: Lee, Jinsung, et al.
Publicado: (2026)

Vanast: Virtual Try-On with Human Image Animation via Synthetic Triplet Supervision
por: Cha, Hyunsoo, et al.
Publicado: (2026)

Generalized Consistency Trajectory Models for Image Manipulation
por: Kim, Beomsu, et al.
Publicado: (2024)

RA-SGG: Retrieval-Augmented Scene Graph Generation Framework via Multi-Prototype Learning
por: Yoon, Kanghoon, et al.
Publicado: (2024)

Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols
por: Kim, Yongwoo, et al.
Publicado: (2025)

Erase at the Core: Representation Unlearning for Machine Unlearning
por: Lee, Jaewon, et al.
Publicado: (2026)

Finding 3D Scene Analogies with Multimodal Foundation Models
por: Kim, Junho, et al.
Publicado: (2025)

Maximizing the Position Embedding for Vision Transformers with Global Average Pooling
por: Lee, Wonjun, et al.
Publicado: (2025)

Catch-Up Mix: Catch-Up Class for Struggling Filters in CNN
por: Kang, Minsoo, et al.
Publicado: (2024)

Think as Needed: Geometry-Driven Adaptive Perception for Autonomous Driving
por: Kim, Donghyun, et al.
Publicado: (2026)

PLATYPUS: Progressive Local Surface Estimator for Arbitrary-Scale Point Cloud Upsampling
por: Kim, Donghyun, et al.
Publicado: (2024)

Delaunay Canopy: Building Wireframe Reconstruction from Airborne LiDAR Point Clouds via Delaunay Graph
por: Kim, Donghyun, et al.
Publicado: (2026)

LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learning
por: Wang, Kaihong, et al.
Publicado: (2025)

Analogical Trajectory Transfer
por: Kim, Junho, et al.
Publicado: (2026)

Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection
por: Chang, Gyusam, et al.
Publicado: (2024)

Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents
por: Kim, Dong-Hee, et al.
Publicado: (2026)

Weakly Supervised Video Scene Graph Generation via Natural Language Supervision
por: Kim, Kibum, et al.
Publicado: (2025)

Directional Textual Inversion for Personalized Text-to-Image Generation
por: Kim, Kunhee, et al.
Publicado: (2025)

CaptionSmiths: Flexibly Controlling Language Pattern in Image Captioning
por: Saito, Kuniaki, et al.
Publicado: (2025)

Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection
por: Park, Kwanyong, et al.
Publicado: (2024)

A Difference-in-Difference Approach to Detecting AI-Generated Images
por: Qi, Xinyi, et al.
Publicado: (2026)

Morphing Tokens Draw Strong Masked Image Models
por: Kim, Taekyung, et al.
Publicado: (2023)

Generalizable Human Gaussian Splatting via Multi-view Semantic Consistency
por: Kim, Jingi, et al.
Publicado: (2026)

ID-EA: Identity-driven Text Enhancement and Adaptation with Textual Inversion for Personalized Text-to-Image Generation
por: Jin, Hyun-Jun, et al.
Publicado: (2025)

Towards a Better Evaluation of Out-of-Domain Generalization
por: Hwang, Duhun, et al.
Publicado: (2024)

Towards Continuous Sign Language Conversation from Isolated Signs
por: Kim, Youngmin, et al.
Publicado: (2026)

Adaptive Self-training Framework for Fine-grained Scene Graph Generation
por: Kim, Kibum, et al.
Publicado: (2024)

Learning Unified Distance Metric Across Diverse Data Distributions with Parameter-Efficient Transfer Learning
por: Kim, Sungyeon, et al.
Publicado: (2023)