5 papers · 1 filter
NoiseController: Towards Consistent Multi-view Video Generation via Noise Decomposition and Collaboration
Haotian Dong, Xin Wang, Di Lin +6
High-quality video generation is crucial for many fields, including the film industry and autonomous driving. However, generating videos with spatiotemporal consistencies remains c…
Visibility-Uncertainty-guided 3D Gaussian Inpainting via Scene Conceptional Learning
Mingxuan Cui, Qing Guo, Yuyi Wang +5
3D Gaussian Splatting (3DGS) has emerged as a powerful and efficient 3D representation for novel view synthesis. This paper extends 3DGS capabilities to inpainting, where masked ob…
MAVIN: Multi-Action Video Generation with Diffusion Models via Transition Video Infilling
Bowen Zhang, Xiaofei Xie, Haotian Lu +3
Diffusion-based video generation has achieved significant progress, yet generating multiple actions that occur sequentially remains a formidable task. Directly generating a video w…
BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout
Kairui Yang, Enhui Ma, Jibin Peng +3
Using synthesized images to boost the performance of perception models is a long-standing research challenge in computer vision. It becomes more eminent in visual-centric autonomou…
CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion
Haotian Dong, Enhui Ma, Lubo Wang +7
Semantic scene completion (SSC) requires an accurate understanding of the geometric and semantic relationships between the objects in the 3D scene for reasoning the occluded object…