OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting
원문 초록
Diffusion-based generative models have revolutionized object-oriented image editing, yet their deployment in realistic object removal and insertion remains hampered by challenges such as the intricate interplay of physical effects and insufficient paired training data. In this work, we introduce OmniPaint, a unified framework that re-conceptualizes object removal and insertion as interdependent processes rather than isolated tasks. Leveraging a pre-trained diffusion prior along with a progressive training pipeline comprising initial paired sample optimization and subsequent large-scale unpaired refinement via CycleFlow, OmniPaint achieves precise foreground elimination and seamless object insertion while faithfully preserving scene geometry and intrinsic properties. Furthermore, our novel CFD metric offers a robust, reference-free evaluation of context consistency and object hallucination, establishing a new benchmark for high-fidelity image editing. Project page: https://yeates.github.io/OmniPaint-Page/
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Revisit What You See: Disclose Language Prior in Vision Tokens for Efficient Guided Decoding of LVLMs
SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding
Causal-LLaVA: Causal Disentanglement for Mitigating Hallucination in Multimodal Large Language Models
Retrieval Visual Contrastive Decoding to Mitigate Object Hallucinations in Large Vision-Language Models
Reducing Object Hallucination in Large Audio-Language Models via Audio-Aware Decoding
Mitigating Object Hallucinations via Sentence-Level Early Intervention
토론
이 논문과 연결된 포럼 글이 아직 없습니다.