AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

RIOcc: Efficient Cross-Modal Fusion Transformer with Collaborative Feature Refinement for 3D Semantic Occupancy Prediction

Baojie Fan, Xiaotian Li, Yuhan Zhou, Yuyu Jiang, Jiandong Tian, Huijie Fan

ICCV 2025 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 0 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 Wavelet Encoder (with Semantic Encoder already present) (ablation)RIOcc · Occ3D-nuScenesmIoU: 53.37 -> 54.21Improved
add Semantic Encoder (with Wavelet Encoder already present) (ablation)RIOcc · Occ3D-nuScenesmIoU: 53.32 -> 54.21Improved
add both Wavelet and Semantic Encoders to the baseline (ablation)RIOcc · Occ3D-nuScenesmIoU: 51.96 -> 54.21Improved
add channel-wise attention only to DBP (ablation)RIOcc · Occ3D-nuScenesmIoU: 53.07 -> 53.70Improved
add grid-wise attention only to DBP (ablation)RIOcc · Occ3D-nuScenesmIoU: 53.07 -> 53.78Improved
combine channel-wise and grid-wise branches (full DBP) (ablation)RIOcc · Occ3D-nuScenesmIoU: 53.07 -> 54.21Improved
increase downsampling layers from 0 to 2 (ablation)RIOcc (no wavelet/semantic encoders) · Occ3D-nuScenesmIoU: 48.21 -> 52.03Improved
increase downsampling layers from 2 to 3 (ablation)RIOcc (no wavelet/semantic encoders) · Occ3D-nuScenesmIoU: 52.03 -> 52.15No clear effect
aggregate local regions in DDA: 1x1 to 5x5 (ablation)RIOcc DDA module · Occ3D-nuScenesmIoU: 47.43 -> 48.21Improved
enlarge aggregation region from 5x5 to 7x7 (ablation)RIOcc DDA module · Occ3D-nuScenesmIoU: 48.21 -> 48.16Hurt
replace addition fusion with DDA (ablation)RIOcc BEV fusion · Occ3D-nuScenesmIoU: 46.58 -> 48.21Improved
replace concatenation fusion with DDA (ablation)RIOcc BEV fusion · Occ3D-nuScenesmIoU: 46.69 -> 48.21Improved

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