OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting
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/
Code (0)
등록된 구현이 없습니다.
Tasks
HallucinationObjectObject HallucinationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
LayerEdit: Disentangled Multi-Object Editing via Conflict-Aware Multi-Layer Learning
Text-driven multi-object image editing which aims to precisely modify multiple objects within an image based on text descriptions, has recently attracted considerable interest. Existing works primarily follow the localiz…
Object LocalizationImage Editing3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting
Scene image editing is crucial for entertainment, photography, and advertising design. Existing methods solely focus on either 2D individual object or 3D global scene editing. This results in a lack of a unified approach…
3D geometryDisentanglementCEI-3D: Collaborative Explicit-Implicit 3D Reconstruction for Realistic and Fine-Grained Object Editing
Existing 3D editing methods often produce unrealistic and unrefined results due to the deeply integrated nature of their reconstruction networks. To address the challenge, this paper introduces CEI-3D, an editing-oriente…
3D ReconstructionCatalogStitch: Dimension-Aware and Occlusion-Preserving Object Compositing for Catalog Image Generation
Generative object compositing methods have shown remarkable ability to seamlessly insert objects into scenes. However, when applied to real-world catalog image generation, these methods require tedious manual interventio…
Image GenerationSIn-NeRF2NeRF: Editing 3D Scenes with Instructions through Segmentation and Inpainting
TL;DR Perform 3D object editing selectively by disentangling it from the background scene. Instruct-NeRF2NeRF (in2n) is a promising method that enables editing of 3D scenes composed of Neural Radiance Field (NeRF) using …
3D Object EditingNeRFObjectSemantic Segmentation