From the 1 of 4 linked papers with an AI index.
4 papers
World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration
Ye Chen, Xuanhong Chen, Yupeng Zhu +23
The paper proposes the World Narrative Model, a framework that separates the specification of a 4D physical scene (geometry, motion, camera, lighting) from pixel generation, enabli…
Agentic Retoucher for Text-To-Image Generation
Shaocheng Shen, Jianfeng Liang, Chunlei Cai +5
Text-to-image (T2I) diffusion models such as SDXL and FLUX have achieved impressive photorealism, yet small-scale distortions remain pervasive in limbs, face, text and so on. Exist…
SMC++: Masked Learning of Unsupervised Video Semantic Compression
Yuan Tian, Xiaoyue Ling, Cong Geng +3
Most video compression methods focus on human visual perception, neglecting semantic preservation. This leads to severe semantic loss during the compression, hampering downstream v…
MoA-VR: A Mixture-of-Agents System Towards All-in-One Video Restoration
Lu Liu, Chunlei Cai, Shaocheng Shen +9
Real-world videos often suffer from complex degradations, such as noise, compression artifacts, and low-light distortions, due to diverse acquisition and transmission conditions. E…