TanGO is proposed, a training-free framework that enables adaptive per-token steering in the tangent space of generative dynamics and substantially reduces structural artifacts and achieves state-of-the-art performance, outperforming existing 3D editing baselines.
Abstract
While recent flow-matching 3D generative models (e.g., VecSet) adopt structured representations, their tokens share global context, causing conventional training-free editing to suffer from semantic artifacts such as collapsed preserved regions or incomplete transformations. To address this, we propose TanGO, a training-free framework that enables adaptive per-token steering in the tangent space of generative dynamics. To realize this selective control, we formulate a one-step optimal control rule and determine the strength of each token's control signal using a von Mises-Fisher inspired directional discrepancy derived from the source and target velocity fields. Experiments show that TanGO substantially reduces structural artifacts and achieves state-of-the-art performance, outperforming existing 3D editing baselines. The code is publicly available at https://github.com/siw00-lim/TanGO.
Instruction-guided 3D editing is essential for interactive content creation, yet it faces a significant bottleneck: the severe scarcity of high-quality paired training data. Existing approaches attempt to bypass this by either relying on slow test-time optimization or training on pseudo-pairs constructed via complex pi...
Hao Wen, Wei-Bin Yun, Hongxing Fan et al.· 0 citations
Self-Geometry, a plug-and-play test-time adaptation pipeline that directly imposes explicit multi-view geometric constraints using 2D pixel correspondences as pseudo ground-truth, achieves consistent improvements in both pose and geometry estimation across VFMs.
Seokhyun Youn, Dahyeon Kye, Sung-Ho Bae et al.· 0 citations
Controllable local editing of 3D assets requires precise target localization and appropriate visual guidance. However, existing methods lack a simple yet accurate way to obtain 3D masks and struggle to achieve the desired edit while faithfully preserving the structure and appearance of non-target regions. To address th...
R. Nie, Chuang Wang, Haitao Zhou et al.· 0 citations
This work introduces a training-free framework for incorporating partial geometric observations into pretrained image-to-3D generative models without retraining or finetuning, and demonstrates that pretrained image-to-3D models can effectively integrate partial geometric observations through explicit test-time guidance...
Jerred Chen, Simon Nikolaus Weber, Ronald Clark· 0 citations
Modern video generators routinely fail at physical dynamics: objects float, trajectories violate gravity, contacts vanish. Standard denoising and flow-matching objectives fit visual data distributions but do not explicitly penalize such physical violations. Existing remedies can improve physical consistency, but typica...
Hai Nguyen-Truong, Tuan-Anh Vu, Dang T. Huynh· 1 citation
A novel optimizer-corrector framework that alternates between gradient steps for objective minimization and guided flow matching to drive the latent state back to the valid shape manifold is introduced, preserving geometric validity without sacrificing expressiveness while remaining computationally feasible on modern 3...
Emilien Seiler, Nicolas Talabot, Ying-Xuan You et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
