6 papers
Feedforward Novel View Synthesis for Heterogeneous Cameras
Meng Wei, Cheng Zhang, Boying Li +4
Feed-forward novel view synthesis has recently shown promising results from sparse posed images, but most existing methods assume that context and target views share a fixed camera…
Attribute Token Arithmetic: Disentangled and Continuous Semantic Control for Visual Autoregressive Models
Xindi Yang, Yicheng Wu, Cheng Zhang +2
Autoregressive text-to-image generation has recently achieved remarkable progress, offering high-fidelity synthesis via a unified generative framework. However, fine-grained semant…
OpenView: Empowering MLLMs with Out-of-view VQA
Qixiang Chen, Cheng Zhang, Chi-Wing Fu +2
Recent multimodal large language models (MLLMs) show great potential in natural image understanding. Yet, they perform well, mainly on reasoning in-view contents within the image f…
ASAP-Textured Gaussians: Enhancing Textured Gaussians with Adaptive Sampling and Anisotropic Parameterization
Meng Wei, Cheng Zhang, Jianmin Zheng +2
Recent advances have equipped 3D Gaussian Splatting with texture parameterizations to capture spatially varying attributes, improving the performance of both appearance modeling an…
Unified Camera Positional Encoding for Controlled Video Generation
Cheng Zhang, Boying Li, Meng Wei +4
Transformers have emerged as a universal backbone across 3D perception, video generation, and world models for autonomous driving and embodied AI, where understanding camera geomet…
PanFlow: Decoupled Motion Control for Panoramic Video Generation
Cheng Zhang, Hanwen Liang, Donny Y. Chen +4
Panoramic video generation has attracted growing attention due to its applications in virtual reality and immersive media. However, existing methods lack explicit motion control an…