AI Paper Atlas

Research map / Video / Video generation

REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents

Rui Tian, Qi Dai, Jianmin Bao, Kai Qiu, Yifan Yang, Chong Luo, Zuxuan Wu, Yu-Gang Jiang

ICCV 2025 · Video › Video generation · approach: Autoregressive long video generation · 15 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 content frame fusion via cross-attention in the VAE decoder (ablation)Reducio-VAE · Pexels reconstructionPSNR: 27.91 -> 35.88Improved
use cross-attention fusion instead of add or linear fusion (ablation)Reducio-VAE · Pexels reconstructionPSNR: 30.86 -> 35.88 (linear), 34.17 -> 35.88 (add)Improved
use middle frame rather than a random frame as content frame (ablation)Reducio-VAE · Pexels reconstructionPSNR: 31.72 -> 35.88Improved
increase temporal downsampling from 2 to 4 at fs=32 (ablation)Reducio-VAE · Pexels reconstructionPSNR: 36.79 -> 35.88Hurt
shift compression from temporal to spatial at identical total factor (ablation)Reducio-VAE · Pexels reconstructionPSNR: 34.14 -> 35.88Improved
increase latent channels from 4 to 16 (ablation)Reducio-VAE · Pexels reconstructionPSNR: 33.17 -> 35.88Improved
increase latent channels from 16 to 32 (ablation)Reducio-VAE · Pexels reconstructionPSNR: 35.88 -> 35.24No clear effect
use 3D convolution instead of 2D convolution in the VAE (ablation)Reducio-VAE · Pexels reconstructionPSNR: 30.22 -> 35.51Improved
use joint 3D attention instead of factorized 2D+1D attention (ablation)Reducio-DiT · UCF-101 FVDFVD: 382.2 -> 337.6Improved
use both semantic and content image conditions rather than semantic only (ablation)Reducio-DiT · UCF-101 FVDFVD: 472.1 -> 337.6Improved
add semantic features to content-only conditioning (ablation)Reducio-DiT · UCF-101 FVD / ISFVD: 363.7 -> 337.6Improved
use patch size 1 with high VAE compression instead of temporal patch size 2 (ablation)Reducio-DiT · UCF-101 FVDFVD: 351.0 -> 337.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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