AI Paper Atlas

Research map / 3D vision / 3D generation

OccScene: Semantic Occupancy-based Cross-task Mutual Learning for 3D Scene Generation

Bohan Li, Xin Jin, Jianan Wang, Yukai Shi, Yasheng Sun, Xiaofeng Wang, Zhuang Ma, Baao Xie, Chao Ma, Xiaokang Yang, Wenjun Zeng

TPAMI 2025 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 5 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 joint diffusion scheme (attached perception model) (ablation)OccScene · SemanticKITTI ablationFID: 28.52 -> 19.86Improved
add joint diffusion scheme (attached perception model) (ablation)OccScene · SemanticKITTI ablationmIoU: 12.94 -> 14.98Improved
add Mamba-based dual alignment (ablation)OccScene · SemanticKITTI ablationFVD: 162.04 -> 113.28Improved
add Mamba-based dual alignment (ablation)OccScene · SemanticKITTI ablationmIoU: 13.41 -> 14.98Improved
use Mamba instead of GRU encoding in alignment (ablation)OccScene · SemanticKITTI ablationFID: 24.54 -> 19.86Improved
use Mamba instead of attention encoding in alignment (ablation)OccScene · SemanticKITTI ablationTime: 4.09 -> 2.76Improved
apply MDA along depth dimension of occupancy (ablation)OccScene · SemanticKITTI ablationFID: 22.12 -> 19.86Improved
apply MDA along temporal dimension of video latent (ablation)OccScene · SemanticKITTI ablationFID: 23.02 -> 19.86Improved
attach gradients between generative and perception models (ablation)MonoScene on NYUv2 · NYUv2mIoU: 27.47 -> 29.78Improved
attach gradients between generative and perception models (ablation)NDC-Scene on NYUv2 · NYUv2mIoU: 30.20 -> 32.12Improved
attach gradients between generative and perception models (ablation)ISO on NYUv2 · NYUv2mIoU: 32.09 -> 33.92Improved
train MonoScene with OccScene synthetic data instead of MagicDrive dataMonoScene · NuScenes-OccupancymIoU: 7.2 -> 10.2Improved

Later papers that compared with this method

1 later accepted paper reports OccScene as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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