3 papers
cs.CV2025
4D Driving Scene Generation With Stereo Forcing
Hao Lu, Zhuang Ma, Guangfeng Jiang +6
Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-sce…
cs.LG2025
Sig-DEG for Distillation: Making Diffusion Models Faster and Lighter
Lei Jiang, Wen Ge, Niels Cariou-Kotlarek +6
Diffusion models have achieved state-of-the-art results in generative modelling but remain computationally intensive at inference time, often requiring thousands of discretization…
cs.CV2025
Matrix-3D: Omnidirectional Explorable 3D World Generation
Zhongqi Yang, Wenhang Ge, Yuqi Li +12
Explorable 3D world generation from a single image or text prompt forms a cornerstone of spatial intelligence. Recent works utilize video model to achieve wide-scope and generaliza…