An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.
Multi-turn Consistent Image Editing
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
abstract
Many real-world applications, such as interactive photo retouching, artistic content creation, and product design, require flexible and iterative image editing. However, existing image editing methods primarily focus on achieving the desired modifications in a single step, which often struggles with ambiguous user intent, complex transformations, or the need for progressive refinements. As a result, these methods frequently produce inconsistent outcomes or fail to meet user expectations. To address these challenges, we propose a multi-turn image editing framework that enables users to iteratively refine their edits, progressively achieving more satisfactory results. Our approach leverages flow matching for accurate image inversion and a dual-objective Linear Quadratic Regulators (LQR) for stable sampling, effectively mitigating error accumulation. Additionally, by analyzing the layer-wise roles of transformers, we introduce a adaptive attention highlighting method that enhances editability while preserving multi-turn coherence. Extensive experiments demonstrate that our framework significantly improves edit success rates and visual fidelity compared to existing methods.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 4years
2026 4roles
background 1polarities
background 1representative citing papers
STARFlow2 presents an autoregressive flow-based architecture for unified multimodal text-image generation by interleaving a VLM stream with a TarFlow stream via residual skips and a unified latent space.
VecSet-Edit edits a mesh by masking and re-denoising a subset of its VecSet latent tokens, preserving untouched regions better than prior voxel-based editors.
Develops a synthetic data pipeline for training sequential decomposition in generative image editing, showing robust gains with complexity and sim-to-real transfer via co-training.
citing papers explorer
-
EditVerse3D: High-Quality 3D Object Editing with Region-Aware Learning
An end-to-end 3D editing framework achieves high-fidelity local edits from coarse bounding boxes and 2D image prompts using region-aware loss reweighting and a large-scale parts-derived training dataset.
-
STARFlow2: Bridging Language Models and Normalizing Flows for Unified Multimodal Generation
STARFlow2 presents an autoregressive flow-based architecture for unified multimodal text-image generation by interleaving a VLM stream with a TarFlow stream via residual skips and a unified latent space.
-
VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image
VecSet-Edit edits a mesh by masking and re-denoising a subset of its VecSet latent tokens, preserving untouched regions better than prior voxel-based editors.
-
Towards Robust Sequential Decomposition for Complex Image Editing
Develops a synthetic data pipeline for training sequential decomposition in generative image editing, showing robust gains with complexity and sim-to-real transfer via co-training.