6 papers
MetaView: Monocular Novel View Synthesis with Scale-Aware Implicit Geometry Priors
Yufei Cai, Xuesong Niu, Hao Lu +3
Current visual generation models are capable of producing high-quality content, yet they lack a coherent perception of the spatial structure. Existing generative novel view synthes…
Boosting Latent Diffusion Models via Disentangled Representation Alignment
John Page, Xuesong Niu, Kai Wu +1
Latent Diffusion Models (LDMs) rely heavily on the compressed latent space provided by Variational Autoencoders (VAEs) for high-quality image generation. Recent studies have attemp…
Visual Generation Tuning
Jiahao Guo, Sinan Du, Jingfeng Yao +7
Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However…
VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction
Sinan Du, Jiahao Guo, Bo Li +8
Unifying multimodal understanding, generation and reconstruction representation in a single tokenizer remains a key challenge in building unified models. Previous research predomin…
A Style is Worth One Code: Unlocking Code-to-Style Image Generation with Discrete Style Space
Huijie Liu, Shuhao Cui, Haoxiang Cao +3
Innovative visual stylization is a cornerstone of artistic creation, yet generating novel and consistent visual styles remains a significant challenge. Existing generative approach…
Group Relative Attention Guidance for Image Editing
Xuanpu Zhang, Xuesong Niu, Ruidong Chen +6
Recently, image editing based on Diffusion-in-Transformer models has undergone rapid development. However, existing editing methods often lack effective control over the degree of…