3 papers
cs.CV2026
Bridging the Manifold Gap: Riemannian Residual Line Search for One-Step Image Editing
Hongzhu Yi, Zhongtian Luo, Tong Li +2
One-step diffusion editors are fast because they avoid inversion and iterative optimization, but a single transport update must be aggressive enough to realize the target prompt an…
cs.CV2026
CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
Jiyuan Wang, Huan Ouyang, Jiuzhou Lin +15
In this paper, we propose Concentrate and Concentrate (CaC), a coarse-to-fine anomaly reward model based on Vision-Language Models. During inference, it first conducts a global tem…
cs.CV2026
GardenDesigner: Encoding Aesthetic Principles into Jiangnan Garden Construction via a Chain of Agents
Mengtian Li, Fan Yang, Ruixue Xiong +3
Jiangnan gardens, a prominent style of Chinese classical gardens, hold great potential as digital assets for film and game production and digital tourism. However, manual modeling…