InstantFusion introduces a lightweight shared latent interface that enables cross-model state translation between heterogeneous image generators. By training model-specific Latent AutoEncoders to project intermediate denoising states into a common latent space, the method aligns states from the same image at matched noise levels and synchronizes their local denoising velocities. This allows seamless denoising transitions across frozen generators, supporting applications such as acceleration, multi-preference composition, on-policy distillation, and cross-model composition.
By Xuanlang Dai, Jiazi Bu, Yujie Zhou, Yuhong Liu, Beichen Zhang, Penghui Yang, Ziyu Liu, Yuhang Zang
arXiv:2604.24136v3 Announce Type: replace
Abstract: Pretrained diffusion models have revolutionized real-world image super-resolution (Real-ISR), but their iterative sampling is computationally prohi...
By Shyang-En Weng, Yi-Cheng Liao, Yu-Syuan Xu, Chia-Hung Yuan, Wei-Chen Chiu, Ching-Chun Huang
arXiv:2607. 02628v1 Announce Type: cross Abstract: While diffusion models have revolutionized image synthesis, their application to real-world inverse problems is often hampered by the need for massive datasets and the difficulty of imposing strict physical constraints.
By Kanishk Awadhiya
arXiv:2506. 13058v2 Announce Type: replace-cross Abstract: Diffusion probabilistic models (DPMs) have demonstrated remarkable success in visual generation.
By Hu Yu, Hao Luo, Xueyang Fu, Jie Huang, Fan Wang, Feng Zhao
arXiv:2606. 00094v1 Announce Type: cross Abstract: Image generative models aim to sample data points from the underlying data manifold, a task that requires learning and decoding a dense, low-dimensional, and compact parameterization space.
By Duoduo Xue, Zhiyu Zhu, Junhui Hou
RecGen3D is a framework that merges feed‑forward reconstruction and diffusion‑based generation to address the trade‑off between reconstruction fidelity and generative plausibility in sparse‑view 3D modeling. By aligning both models in a shared canonical space and using decoupled cooperative learning, the system stabilizes training and allows the reconstruction module to supply canonical geometric anchors while the diffusion generator refines and completes the structure. Experiments show that RecGen3D outperforms existing methods in producing complete and consistent 3D models from sparse observations.
By Zhisheng Huang, Jiahao Chen, Cheng Lin, Chenyu Hu, Hanzhuo Huang, Zhengming Yu, Mengfei Li, Yuheng Liu, Zekai Gu, Zibo Zhao, Yuan Liu, Xin Li, Wenping Wang
arXiv:2606. 24874v1 Announce Type: cross Abstract: Sparse voxel representation has emerged as a scalable foundation for image-to-3D Gaussian Splatting (3DGS) generation, yet current methods struggle to preserve high-frequency visual details of input images due to two structural bottlenecks.
By Haorui Ji, Weizhe Liu, Hongdong Li, Hengkai Guo
arXiv:2608.14740v2 Announce Type: replace
Abstract: Unified image and video creation requires a model to follow diverse instructions while preserving identity, geometry, and temporal structure from v...
By Zhefan Rao, Bin Zou, Xuanhua He, Chong Hou Choi, Yanheng Li, Rui Liu, Haoxuan Che, Qifeng Chen
arXiv:2607. 17611v1 Announce Type: cross Abstract: Multi-exposure fusion (MEF) expands the luminance range beyond what a single exposure can capture.
By Sangmin Han, Jinho Kim, Jinwoo Kim, Dongyoung Kim, Seon Joo Kim
Recent advances in diffusion models have shown impressive performance in controllable image generation and dense prediction tasks. However, existing approaches typically treat diffusion-based controllable generation and dense prediction as separate tasks, overlooking the potential benefits of jointly modeling the heterogeneous distributions.
arXiv:2608. 10544v1 Announce Type: cross Abstract: Image restoration is fundamentally constrained by the tradeoff between distortion and perception: minimizing pixel-wise error yields over-smoothed results, whereas optimizing for perceptual realism often introduces structural deviations.
By Sangwoo Jo, Donggeun Ko, Jayeon Kang, Youngsang Kwak, Jaehwa Kwak, Sungjoon Choi
We study the challenging problem of novel view video synthesis from single images or monocular videos. Existing methods, which operate under the assumption that pre-trained video models lack native novel view synthesis capability and enforce view alignment via camera conditioning, task-specific fine-tuning, or stepwise hard denoising guidance, often suffer from artifacts and compromised global scene consistency.