前馈3D编辑从语义部分变换中学习
Feedforward 3D Editing Learns from Semantic-Part Transformation
AI总结：
提出Pxform数据集和PartFlow网络，通过语义部分变换实现高质量前馈3D编辑，在几何和外观编辑基准上达到最优性能。
摘要：
3D编辑是可扩展3D内容创作的基本能力。虽然图像编辑已迅速向大规模前馈生成范式发展，但3D AI生成仍以无需训练的编辑流程为主。前馈3D编辑的核心挑战在于缺乏高质量配对监督。可编辑的3D资产需要同时保持几何、多视图一致性、结构连贯性和局部编辑可控性。现有的3D编辑数据集通常依赖于独立生成的资产、图像介导的重建或狭窄的编辑分类，导致定位不准确、保持性弱、编辑边界模糊和语义一致性有限。在这项工作中，我们引入了一个新视角：可扩展的前馈3D编辑应从语义部分变换中学习。基于这一见解，我们提出了Pxform，一个高质量的3D编辑数据集，包含超过10万对七种编辑类型的一致前后编辑对。我们的流程不是将对象视为无结构形状，而是直接将编辑锚定在语义3D部分。基于Pxform，我们进一步提出了PartFlow，一个前馈3D编辑网络，它将源感知潜在控制注入预训练的3D生成先验中。PartFlow引入了掩码感知速度保持和渲染空间一致性监督，以共同提高编辑保真度和源保持，同时在推理时不需要3D编辑掩码。大量实验表明，高质量的语义部分监督显著改进了可扩展的3D编辑，使PartFlow在几何和外观编辑基准上均达到了最先进的性能。
英文摘要：
3D editing is a fundamental capability for scalable 3D content creation. While image editing has rapidly evolved toward large-scale feedforward generative paradigms, 3D AI generation remains dominated by training-free editing pipelines. A central challenge of feedforward 3D editing lies in the lack of high-quality paired supervision. Editable 3D assets require simultaneous preservation of geometry, multi-view consistency, structural coherence, and localized edit controllability. Existing 3D editing datasets often rely on independently generated assets, image-mediated reconstruction or narrow edit taxonomies, leading to inaccurate localization, weak preservation, blurred edit boundaries, and limited semantic consistency. In this work, we introduce a new perspective: scalable feedforward 3D editing should be learned from semantic-part transformations. Based on this insight, we propose Pxform, a high-quality 3D editing dataset with over 100K consistent before/after editing pairs across seven edit types. Instead of treating objects as unstructured shapes, our pipeline grounds edits directly in semantic 3D parts. Built upon Pxform, we further propose PartFlow, a feedforward 3D editing network that injects source-aware latent control into pretrained 3D generative priors. PartFlow introduces mask-aware velocity preservation and render-space consistency supervision to jointly improve edit fidelity and source preservation, while requiring no 3D edit mask during inference. Extensive experiments demonstrate that high-quality semantic-part supervision substantially improves scalable 3D editing, enabling PartFlow to achieve state-of-the-art performance on both geometric and appearance editing benchmarks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
