arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2605.07385cs.GRcs.CV
收藏

速度空间3D资产编辑

Velocity-Space 3D Asset Editing

Tsinghua University(清华大学);South China University of Technology(华南理工大学);Peng Cheng Laboratory(鹏城实验室)

Hao Liu, Yuxuan Lin, Jingfeng Guo, Ruihang Chu, Junjie Wang, Ruotong Li, Yujiu Yang

AI总结:

本文提出VS3D框架,通过在采样器内部进行针对性干预,解决3D编辑中局部修改与保持其余部分的三大问题,包括身份泄漏、编辑信号放大和身份拖拽。

摘要:

对3D资产进行局部编辑,修改目标区域同时保持其余部分,是原生3D编辑的基本要求。现有方法通过生成器外部的机制强制局部性,如手动3D掩码、事后体素合并或2D多视图提升。这些方法均未在腐败实际起源处干预:在ODE采样器内部。为了实现忠实的局部编辑,修正流生成器的速度场应在目标编辑区域强大,而在保持内容上消失。然而,单一的速度场难以同时满足这两个要求,导致三个问题:(i)身份泄漏使编辑信号在保持区域非零;(ii)没有专门的编辑放大通道,因此加强编辑不可避免地扰动身份;(iii)在几何和材质阶段的身份拖拽,其中全局条件将每个标记拉向目标。我们提出VS3D(速度空间3D资产编辑),一种无反向、无训练、无掩码的框架,通过在采样器内部进行针对性干预解决每个问题。VS3D集成了三个互补模块,每个模块对应编辑流水线的特定阶段。Reconstruction-Anchored Source Injection (RASI) 通过将无条件嵌入转换为每步、资产特定的锚点,通过源重建校准来吸收身份泄漏。Partial-Mean Guidance (PMG) 通过对比高质量和低质量子样本估计的速度差异,放大编辑信号,仅在存在一致编辑的地方激活。Twin-Agreement Residual injection (TAR) 让采样器在几何和材质阶段逐个决定应保留什么。

英文摘要:

Local 3D asset editing requires modifying a target region while preserving the rest. Existing methods enforce locality through mechanisms external to the generator, such as manual 3D masks, post-hoc voxel merging, or 2D multi-view lifting. None intervene where the corruption originates: inside the ODE sampler. For faithful local editing, a rectified-flow generator's velocity field should be strong over the target region while vanishing on preserved content. Yet a single velocity field can hardly satisfy both requirements, leading to three problems: (i) identity leakage that keeps the edit signal non-zero on preserved regions; (ii) no dedicated edit-amplification channel, so strengthening the edit perturbs identity; and (iii) identity drag at the geometry and material stages, where a global condition pulls every token toward the target. We propose VS3D (Velocity-Space 3D Asset editing), an inversion-free, training-free, and mask-free framework that derives edit and preserve signals by comparing the frozen model's source- and target-conditioned responses and realizes this principle through three stage-specific modules. Reconstruction-Anchored Source Injection (RASI) absorbs identity leakage by turning the unconditional embedding into a per-step, asset-specific anchor calibrated through source reconstruction. Partial-Mean Guidance (PMG) amplifies the edit signal by contrasting high- and low-quality subsample estimates of the velocity difference, active only where a consistent edit exists. Twin-Agreement Residual Injection (TAR) lets the sampler decide token by token what to preserve at the geometry and material stages. Experiments on diverse 3D assets show that VS3D outperforms state-of-the-art native-3D and 2D-lifted editors, demonstrating the effectiveness of velocity-space editing for training-free 3D asset editing. Code is publicly available at https://github.com/LHaoooo/VS3D.

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。

↑