AI Paper Atlas

Research map / Video / Video generation

Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance

Naifu Xue, Zhaoyang Jia, Jiahao Li, Bin Li, Zihan Zheng, Yuan Zhang, Yan Lu

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add contextual semantic guidance (CSG) to the single-step diffusion generator (ablation)S2VC · HEVC-BDISTS BD-rate (%): 22.08 -> 14.06 (w/o CSG vs CSG only)Improved
add DINOv3 semantic distillation on top of CSG (ablation)S2VC · HEVC-BDISTS BD-rate (%): 14.06 -> 0.00Improved
add DINOv3 semantic distillation on top of CSG (ablation)S2VC · UVGDISTS BD-rate (%): 29.71 -> 0.00Improved
add temporal consistency guidance (TCG) blocks (ablation)S2VC · UVGFloLPIPS BD-rate (%): 46.88 -> 28.46 (w/o TCG vs TCG only)Improved
add cascade training (gradient propagation across frames) to TCG (ablation)S2VC · HEVC-BFloLPIPS BD-rate (%): 14.66 -> 0.00Improved
use S2VC instead of PLVC (perceptual codec)video codec · HEVC-B, UVG, MCL-JCVDISTS BD-rate saving (%): 57.69%, 32.69%, 64.49% (average 51.62%)Improved
use S2VC instead of other codecs on motion-aware metricvideo codec · UVGFloLPIPSNo clear effect
use S2VC instead of other codecs on realismvideo codec · HEVC-B, UVG, MCL-JCVFIDImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy