AI Paper Atlas

Research map / Video / Video generation

Video-SVD: Efficient Video Diffusion via Orthogonal Basis Composition

Zhang Wan, Yu Li, Tianze Huang, Haochen Li, Juan Cao, Sheng Tang

ICML 2026 · Video › Video generation · approach: Efficient video diffusion models

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 RoPE positional residual to basis-only attention (ablation)Video-SVD · Wan2.1-1.3BVBench: 71.53 -> 76.51Improved
add content residual to basis-only attention (ablation)Video-SVD · Wan2.1-1.3BVBench: 71.53 -> 78.24Improved
add both residual streams (ablation)Video-SVD · Wan2.1-1.3BVBench: 71.53 -> 81.76Improved
add both residual streams (ablation)Video-SVD · Wan2.1-1.3Bspeedup: 1.95x -> 1.75xHurt
use uniform instead of adaptive Top-5% sampling for Stage 2 (ablation)Video-SVD · Wan2.1-1.3Blatency (s): 283.6 -> 268.0Improved
use adaptive Top-5% instead of uniform sampling (ablation)Video-SVD · Wan2.1-1.3BPSNR: 27.50 -> 27.53No clear effect
use uniform instead of random sampling (ablation)Video-SVD · Wan2.1-1.3BPSNR: 27.46 -> 27.50No clear effect
use checkpoint-adaptive bases instead of LinformerVideo-SVD · Wan2.1-1.3BPSNR: 20.8 -> 27.5Improved
use Video-SVD instead of SVG on high-motion videosSVG · pre-softmax reconstruction errorMSE: 0.250 -> 0.090Improved
increase basis number K (ablation)Video-SVD · Wan2.1-1.3Bquality vs speedMixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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