10 papers · 1 filter
Position Forcing: Self-Conditioning 3D Generation
Ziheng Ouyang, Zeqiang Lai, Jiarui Chen +7
Recent single-stage 3D generative models commonly adopt VecSet representations, encoding 3D shapes as unordered sets of latent tokens. However, compared with two-stage methods that…
MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers
Jiarui Chen, Zeqiang Lai, Jiangshan Wang +5
Sparse attention is a primary approach to reducing the latency of diffusion transformers in long-sequence generation tasks, such as video and high-resolution 3D asset generation. H…
DreamStyle3D: Efficient 3D Stylized Asset Generation via Dual-Attention Disentanglement
Kai Wang, Ziheng Ouyang, Xuying Zhang +2
With the growth of gaming, animation, and virtual reality industries, the demand for efficient generation of stylized 3D assets is rapidly increasing. However, existing approaches…
Direct 3D-Aware Object Insertion via Decomposed Visual Proxies
Jingbo Gong, Yikai Wang, Yushi Lan +6
Object insertion aims to seamlessly composite a reference object into a specified region of a background image. Recent diffusion-based methods achieve high visual quality but formu…
Mixture of Style Experts for Diverse Image Stylization
Shihao Zhu, Ziheng Ouyang, Yijia Kang +5
Diffusion-based stylization has advanced significantly, yet existing methods are limited to color-driven transformations, neglecting complex semantics and material details. We intr…
The Consistency Critic: Correcting Inconsistencies in Generated Images via Reference-Guided Attentive Alignment
Ziheng Ouyang, Yiren Song, Yaoli Liu +4
Previous works have explored various customized generation tasks given a reference image, but they still face limitations in generating consistent fine-grained details. In this pap…
OmniRefiner: Reinforcement-Guided Local Diffusion Refinement
Yaoli Liu, Ziheng Ouyang, Shengtao Lou +1
Reference-guided image generation has progressed rapidly, yet current diffusion models still struggle to preserve fine-grained visual details when refining a generated image using…
AgeBooth: Controllable Facial Aging and Rejuvenation via Diffusion Models
Shihao Zhu, Bohan Cao, Ziheng Ouyang +3
Recent diffusion model research focuses on generating identity-consistent images from a reference photo, but they struggle to accurately control age while preserving identity, and…
OneVAE: Joint Discrete and Continuous Optimization Helps Discrete Video VAE Train Better
Yupeng Zhou, Zhen Li, Ziheng Ouyang +8
Encoding videos into discrete tokens could align with text tokens to facilitate concise and unified multi-modal LLMs, yet introducing significant spatiotemporal compression compare…
K-LoRA: Unlocking Training-Free Fusion of Any Subject and Style LoRAs
Ziheng Ouyang, Zhen Li, Qibin Hou
Recent studies have explored combining different LoRAs to jointly generate learned style and content. However, existing methods either fail to effectively preserve both the origina…