Search papers, labs, and topics across Lattice.
The Large Processing Model (LPM) is a novel diffusion-based generative framework designed for photorealistic video restoration, specifically addressing the complex degradations found in user-generated content (UGC). By integrating large-scale data engineering, foundation-model training, and an efficient inference mechanism, LPM achieves high-fidelity restoration of long videos while maintaining temporal consistency. Deployed at Kuaishou, LPM not only enhances video quality but also reduces bandwidth costs significantly, demonstrating its practical scalability in industrial applications.
LPM restores user-generated videos with such high fidelity that it accounts for 45% of Kuaishou's total viewing time while slashing bandwidth costs by 20%.
We present the Large Processing Model (LPM), a diffusion-based generative framework for photorealistic video restoration under complex, in-the-wild degradations. To our knowledge, LPM is the first generative video restoration model deployed at industrial scale. LPM addresses the diverse degradations in user-generated content (UGC) through a unified system encompassing large-scale data engineering, foundation-model training, and efficient inference. Its enhanced architecture, progressive training strategy, and temporal-pyramid inference mechanism jointly enable high-fidelity, temporally consistent restoration of arbitrarily long videos across the broad content distribution encountered on UGC platforms. LPM has been deployed in production at Kuaishou, where videos processed by the model account for approximately 45% of total viewing time, delivering consistent improvements across key quality-of-experience metrics. Beyond perceptual enhancement, LPM delivers substantial system-level benefits: at comparable perceptual quality, it reduces bitrate by 20% relative to Kuaishou's in-house codec, yielding annual bandwidth cost savings on the order of hundreds of millions. Its low serving cost also enables integration into products such as Kling, demonstrating that generative restoration can be practical, scalable, and cost-effective for large-scale video processing.
