AI Paper Atlas

Research map / 3D vision / 3D generation

SparseWorld-TC: Trajectory-Conditioned Sparse Occupancy World Model

Jiayuan Du, Yiming Zhao, Zhenglong Guo, Yong Pan, Wenbo Hou, Zhihui Hao, Kun Zhan, Qijun Chen

CVPR 2026 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction · 3 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 predicted trajectory conditioning (ablation)SparseWorld-TC-Small · Occ3D-nuScenes 1-3savg mIoU (%): 15.44 -> 21.57Improved
use ground-truth trajectory instead of predicted (ablation)SparseWorld-TC-Small · Occ3D-nuScenes 1-3savg mIoU (%): 21.57 -> 25.60Improved
add predicted trajectory conditioning (ablation)SparseWorld-TC-Small · Occ3D-nuScenes 1-3savg IoU (%): 32.19 -> 44.76Improved
random-ensemble horizon supervision instead of fixed horizon (ablation)SparseWorld-TC-Large · Occ3D-nuScenes 1-8savg mIoU (%): 20.36 -> 22.33Improved
random-ensemble horizon supervision instead of fixed horizon (ablation)SparseWorld-TC-Large · Occ3D-nuScenes 1-8savg IoU (%): 43.25 -> 45.35Improved
swap ResNet-50 for DINOv3-Base backbone (ablation)SparseWorld-TC-Large · Occ3D-nuScenes 1-3savg mIoU (%): 26.42 -> 29.89Improved
increase anchors from 600x128 to 4800x16 (Small to Large) (ablation)SparseWorld-TC · Occ3D-nuScenes 1-3savg mIoU (%) / FPS: mIoU 25.60 -> 26.42; FPS 9.35 -> 3.58Mixed
sparse-anchor transformer instead of VAE/BEV pipeline (vs COME)SparseWorld-TC-Large · Occ3D-nuScenes 1-3savg mIoU (%): 22.26 -> 26.42Improved
camera-only sparse model vs GT-occupancy-input COME on long horizonSparseWorld-TC-Large · Occ3D-nuScenes 1-8savg IoU (%): 29.96 -> 45.35Improved

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