SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution

TL;DR

SeeClear introduces a novel semantic distillation framework for video super-resolution that improves detail consistency across frames by integrating semantic controls, dynamic pixel alignment, and a specialized diffusion process.

Contribution

This work presents a new VSR framework combining semantic distillation, instance-centric alignment, and a novel diffusion mechanism, advancing the state-of-the-art in perceptually realistic video enhancement.

Findings

Outperforms existing diffusion-based VSR methods in quality.

Effectively maintains detail consistency across frames.

Demonstrates superior perceptual realism in generated videos.

Abstract

Diffusion-based Video Super-Resolution (VSR) is renowned for generating perceptually realistic videos, yet it grapples with maintaining detail consistency across frames due to stochastic fluctuations. The traditional approach of pixel-level alignment is ineffective for diffusion-processed frames because of iterative disruptions. To overcome this, we introduce SeeClear--a novel VSR framework leveraging conditional video generation, orchestrated by instance-centric and channel-wise semantic controls. This framework integrates a Semantic Distiller and a Pixel Condenser, which synergize to extract and upscale semantic details from low-resolution frames. The Instance-Centric Alignment Module (InCAM) utilizes video-clip-wise tokens to dynamically relate pixels within and across frames, enhancing coherency. Additionally, the Channel-wise Texture Aggregation Memory (CaTeGory) infuses extrinsic knowledge, capitalizing on long-standing semantic textures. Our method also innovates the blurring diffusion process with the ResShift mechanism, finely balancing between sharpness and diffusion effects. Comprehensive experiments confirm our framework's advantage over state-of-the-art diffusion-based VSR techniques. The code is available: https://github.com/Tang1705/SeeClear-NeurIPS24.