arXiv:2606.13345v2 Announce Type: replace
Abstract: Existing 3D scene editing methods typically rely on per-scene optimization over explicit 3D representations or cascaded edit-and-reconstruct pipeli...
By Xinnan Zhu, Ruijie Xu, Jiayu Ying, Daoguo Dong, Jiachen Xu, Yuan Xie, Xin Tan
arXiv:2605.04412v3 Announce Type: replace
Abstract: 3D asset generation plays a pivotal role in fields such as gaming and virtual reality, enabling the rapid synthesis of high-fidelity 3D objects fro...
By Yiran Qiao, Yiren Lu, Yunlai Zhou, Disheng Liu, Linlin Hou, Rui Yang, Yu Yin, Jing Ma
Stylos is a single-forward 3D Gaussian framework that performs 3D style transfer from a single image to a multi-view collection without requiring per-scene optimization or precomputed poses. It uses a Transformer backbone with geometry and style pathways, employing self-attention for geometric fidelity and global cross-attention for visual consistency, and introduces a voxel-based 3D style loss to align scene features with style statistics. Experiments on multiple datasets show that Stylos achieves high-quality, zero-shot stylization that generalizes to unseen categories, scenes, and styles.
By Hanzhou Liu, Jia Huang, Mi Lu, Srikanth Saripalli, Peng Jiang
arXiv:2608.25461v1 Announce Type: cross
Abstract: Using conditional image generators, texture artists can explore many single-view looks for an existing 3D shape. Despite impressive progress, state-o...
By Chenyue Cai, Anita Hu, James Lucas, Szymon Rusinkiewicz, Masha Shugrina
The paper introduces SuRe, a framework that mitigates semantic leakage in image-guided zero-shot style transfer by regulating key–value coupling in diffusion model self‑attention. SuRe disrupts the native correspondence between style keys and values through a value shuffle technique, then progressively recouples them to preserve style fidelity while improving content similarity. Experiments on SD1.5, SDXL, SD3, and FLUX.1‑dev show that SuRe outperforms 18 existing methods in maintaining style similarity and consistently enhancing content similarity, with natural generalization to multi‑style transfer.
By Haojun Tang, Qiwei Lin, Tongda Xu, Wenda Zhao, Yian Zhao, Yu Zhang, Lida Huang, Yan Wang
Recent 3D foundation models can generate high-quality assets from a single image, but degrade markedly on unconstrained multi-image inputs, often producing distorted geometry, over-smoothed textures, and chaotic colors. We argue that this failure stems not from limited model capacity, but from a mismatch between single-image cross-attention and the multi-image setting: existing models lack a principled way to decide which image each 3D voxel should trust at each denoising step.
arXiv:2609.23169v1 Announce Type: new
Abstract: High-quality texture generation is essential for creating realistic and production-ready 3D assets. Recent multi-view diffusion methods have shown prom...
By Yibo Zhang, Ze Yuan, Nan Cao, Li Zhang, Yan-Pei Cao, Yuan-Chen Guo, Rui Ma
Large-scale text-to-image models are attractive backbones for dense prediction because RGB generation pretraining learns rich semantic, structural, and geometric priors. Existing generative and editing approaches reuse these priors by casting dense prediction as target generation: annotations such as depth, normals, alpha mattes, masks, and heatmaps are encoded into an RGB-trained VAE latent space and decoded back as image-like targets.
SafeStyle is a training‑free framework that injects calibrated style residuals into frozen diffusion models for reference‑guided stylization. It estimates style‑supported and content‑associated subspaces from small calibration sets, then transports purified style evidence across adaptive spatial granularity while limiting its influence with a residual‑norm budget. Experiments on texture‑ and geometry‑dominant styles show high DINO style similarity (0.432–0.474) with minimal semantic leakage (0.8%).
By Zhangping Yang, Min Li, Song Yan, Rong Gao, Xinliang Bi, Guanye Xiong, Yujie He
The paper introduces Abstraction in Style (AiS), a generative framework that separates structural abstraction from visual stylization. AiS first creates an abstraction proxy that reinterprets a target image’s structure according to the abstraction logic of a given style, then renders this proxy to produce a stylized output. By learning transformations from visual exemplars without explicit geometric supervision, AiS enables a broader range of stylistic transformations, improves controllability, and allows more expressive stylization.
By Min Lu, Yuanfeng He, Anthony Chen, Jianhuang He, Pu Wang, Daniel Cohen-Or, Hui Huang
arXiv:2609.38136v1 Announce Type: new
Abstract: Style transfer aims to render target content in the style of a reference image, but existing methods often suffer from content leakage, where objects,...
By Teng Zhou, Yunhao Chen
The paper introduces Chameleon, a two‑stage training framework for cross‑domain image compositing that separates style and content representations. It first trains a ChameleonEncoder using Joint Hard Contrastive Learning to disentangle style and content, then applies Spatio‑Temporal Attention Gating within a diffusion transformer to stylize the foreground while preserving its identity. The authors also release ChameleonDataset, the first large‑scale training set for cross‑domain compositing, and demonstrate that Chameleon outperforms existing in‑domain, cross‑domain, and commercial models in both plausibility and stylistic fidelity.
By Sukhun Ko, Soo Ye Kim, Jihyong Oh