AI Paper Atlas

Research map / 3D vision / 3D generation

Streaming Dense Voxel Representations for 3D Occupancy Prediction

Seokha Moon, Janghyun Baek, Yujin Jeong, Daewon Chae, Giseop Kim, Jungbeom Lee, Jinkyu Kim, Sunwook Choi

ECCV 2026 · 3D vision › 3D generation · approach: Vision-based 3D occupancy prediction

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 StreamAgg temporal voxel aggregation to the single-frame base (ablation)StreamOcc base · Occ3D-nuScenesmIoU: 36.8 -> 40.4Improved
add an auxiliary detection head to StreamAgg (ablation)StreamAgg · Occ3D-nuScenesmIoU_D: 35.4 -> 36.3Improved
add QueryAgg to StreamAgg (ablation)StreamAgg · Occ3D-nuScenesmIoU_D: 35.4 -> 38.1Improved
add Adaptive Residual Refinement to naive voxel streaming (ablation)Naive voxel streaming · Occ3D-nuScenesmIoU: 38.72 -> 39.84Improved
add Semantic Supervision to the refinement module (ablation)StreamAgg refinement · Occ3D-nuScenesmIoU: 39.84 -> 40.25Improved
add Geometry Supervision to the refinement module (ablation)StreamAgg refinement · Occ3D-nuScenesmIoU: 40.25 -> 40.37Improved
add voxel-to-query detector (V2Q) alone to StreamAgg (ablation)StreamAgg · Occ3D-nuScenesmIoU: 40.37 -> 40.06Hurt
add image-to-query detector (I2Q) alone to StreamAgg (ablation)StreamAgg · Occ3D-nuScenesmIoU: 40.37 -> 40.42No clear effect
add V2Q on top of I2Q (ablation)StreamAgg + I2Q · Occ3D-nuScenesmIoU: 40.42 -> 40.78Improved
add Dynamic Query Aggregation (DQA) on top of I2Q+V2Q (ablation)StreamAgg + I2Q + V2Q · Occ3D-nuScenesmIoU: 40.78 -> 41.90Improved
replace QueryAgg with Spatial Cross-Attention for image-to-voxel aggregation (ablation)StreamAgg · Occ3D-nuScenesmIoU_D: 38.12 -> 35.77Hurt
use QueryAgg instead of Spatial Cross-Attention on latency (ablation)StreamAgg · Occ3D-nuSceneslatency (ms): 95.2 -> 83.3Improved

Earlier methods this paper compares with

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