11 papers
Conditioning Residuals for Diffusion Models via Representation Feedback
Weilai Xiang, Hongyu Yang, Di Huang +1
The paper introduces Conditioning Residuals, a lightweight feedback mechanism that injects compact feature summaries back into the conditioning embeddings of diffusion model backbo…
Spatial Gram Alignment for Ultra-High-Resolution Image Synthesis
Jinjin Zhang, Xiefan Guo, Di Huang
Modern ultra-high-resolution image synthesis relies heavily on the robust generative capacity of large-scale pre-trained Latent Diffusion Models (LDMs). While recent representation…
What Makes Synthetic Data Effective in Image Segmentation
Jinjin Zhang, Xiefan Guo, Yizhou Jin +2
Driven by rapid advances in large-scale generative models, synthetic data has emerged as a promising solution for visual understanding. While modern diffusion models achieve remark…
Catalyst4D: High-Fidelity 3D-to-4D Scene Editing via Dynamic Propagation
Shifeng Chen, Yihui Li, Jun Liao +2
Recent advances in 3D scene editing using NeRF and 3DGS enable high-quality static scene editing. In contrast, dynamic scene editing remains challenging, as methods that directly e…
TokenSplat: Token-aligned 3D Gaussian Splatting for Feed-forward Pose-free Reconstruction
Yihui Li, Chengxin Lv, Zichen Tang +2
We present TokenSplat, a feed-forward framework for joint 3D Gaussian reconstruction and camera pose estimation from unposed multi-view images. At its core, TokenSplat introduces a…
MSN: Multi-directional Similarity Network for Hand-crafted and Deep-synthesized Copy-Move Forgery Detection
Liangwei Jiang, Jinluo Xie, Yecheng Huang +3
Copy-move image forgery aims to duplicate certain objects or to hide specific contents with copy-move operations, which can be achieved by a sequence of manual manipulations as wel…