3D reconstruction from a lengthy video stream input poses a dilemma for feed-forward reconstruction models (FFRMs), that a whole-stream inference context cannot be retained under limited GPU memory.Recent studies seek to resolve this problem via a trade-off between the integrity of inference context and GPU memory usag...
H. Mao, Jun-Jun Jiang, Youyu Chen et al.· 0 citations
This work introduces S3VD, a Semantic-Guidance Spatio-Temporal Scanning framework for video deraining, featuring two key innovations: Multi-Scale Semantic Fusion (MSSF) Module and Spatio-Temporal Scanning Fusion (STSF) Module.
Kui Jiang, Yiang Chen, Yan Luo et al.· 0 citations
A novel framework, VFC-Net, which generates a uniformly distributed coarse point cloud to effectively guide dense reconstruction and introduces a lightweight VoxAttn module in both stages to efficiently capture missing geometric structures.
Guo-Qing Zhang, Wen-Bo Zhao, Yuan-Chao Bai et al.· IEEE Transactions on Image P...· 0 citations
ViP-Rig is a visual-prompted framework that supports both prompt-first rigging and result-guided editing by injecting features extracted from user-drawn or edited 2D skeletal and rigidity prompts into frozen pretrained backbones into a frozen pretrained autoregressive generator.
Zihan Qin, Ming-Ze Sun, Yifan Mao et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
