FlashWorld: High-quality 3D Scene Generation within Seconds
Paper
• 2510.13678 • Published
• 73
VideoGeneration
-
-
Temporal Alignment Guidance: On-Manifold Sampling in Diffusion Models
Paper • 2510.11057 • Published • 31
CVD-STORM: Cross-View Video Diffusion with Spatial-Temporal Reconstruction Model for Autonomous Driving
Paper • 2510.07944 • Published • 25Note VAE的4D改进和Gaussian Splatting Decoder
SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
Paper • 2510.12784 • Published • 20Note 通过图像的视觉能力来给自己打分，从而得到比较好的生成能力，可以作为我们的baseline，提升物理效果
AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4D Scenes
Paper • 2510.10670 • Published • 19Note 生成特定人物姿态和运动、可指定相机运动的视频生成