AI Paper Atlas

Research map / Video / Video generation

OctWorld: Long-Range World-Consistent Video Generation with Octree-based 3D Mapping

Zelong Lv, Sicheng Xu, Jianfeng Xiang, Yue Dong, Ruicheng Wang, Yu Deng, Guangzhong Sun, Jiaolong Yang

ECCV 2026 · Video › Video generation · approach: World-model video generation · 2 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
use OctMap memory instead of fixed-resolution TSDF (36 frames) (ablation)OctWorld · Re10K reverse trajectory ablationLPIPS: 0.1996 -> 0.1412Improved
use OctMap memory instead of fixed-resolution TSDF (36 frames) (ablation)OctWorld · Re10K reverse trajectory ablationChamfer distance: 0.0345 -> 0.0252Improved
add OctMap spatial condition (ablation)OctWorld · Re10K reverse trajectory ablationLPIPS: 0.2128 -> 0.1412Improved
use TSDF instead of point cloud memory (16 frames) (ablation)OctWorld · Re10K reverse trajectory ablationChamfer distance: 0.0916 -> 0.0556Improved
increase noise augmentation level from 0 to 3 (ablation)OctWorld · WorldScore static3D consistency: 67.18 -> 71.67Improved
increase noise augmentation level from 0 to 3 (ablation)OctWorld · Re10K reverse trajectoryLPIPS: 0.1412 -> 0.1633Hurt
use OctMap instead of fixed TSDF at voxel 0.002 (ablation)OctWorld · Reprojection renderingPSNR: 22.08 -> 23.47Improved
use TSDF with smaller voxel size (ablation)OctWorld · Reprojection renderingmemory: 1.37 GB -> OOM at 0.001Hurt
use OctWorld instead of Gen3COctWorld · Re10K reverse trajectoryLPIPS: 0.1933 -> 0.1633Improved
use OctWorld instead of VoyagerOctWorld · WorldScore camera controlscore: 46.60 -> 39.12Hurt
use OctWorld instead of Gen3COctWorld · WorldScore photometric consistencyscore: 68.46 -> 77.01Improved

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