4 papers
I3DM: Implicit 3D-aware Memory Retrieval and Injection for Consistent Video Scene Generation
Jia Li, Han Yan, Yihang Chen +6
Despite remarkable progress in video generation, maintaining long-term scene consistency upon revisiting previously explored areas remains challenging. Existing solutions rely eith…
BachVid: Training-Free Video Generation with Consistent Background and Character
Han Yan, Xibin Song, Yifu Wang +3
Diffusion Transformers (DiTs) have recently driven significant progress in text-to-video (T2V) generation. However, generating multiple videos with consistent characters and backgr…
BAG: Body-Aligned 3D Wearable Asset Generation
Zhongjin Luo, Yang Li, Mingrui Zhang +8
While recent advancements have shown remarkable progress in general 3D shape generation models, the challenge of leveraging these approaches to automatically generate wearable 3D a…
PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image
Han Yan, Mingrui Zhang, Yang Li +2
We present PhyCAGE, the first approach for physically plausible compositional 3D asset generation from a single image. Given an input image, we first generate consistent multi-view…