AI Paper Atlas

Research map / Detection and segmentation / CNN features

E²I-VRWKV: Explicit EPI-Representation and Interaction-Aware Vision-RWKV for Light Field Semantic Segmentation

Wei Zhang, Chen Jia, Xu Cheng, Fan Shi, Hui Liu, Shengyong Chen

ICML 2026 · Detection and segmentation › CNN features · approach: Context modeling for semantic segmentation

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 GC-Gate geometric gating instead of naive concatenation (ablation)E2I-VRWKV · UrbanLF-SynmIoU: 84.68 -> 86.46Improved
add VRWKV mixer (ablation)E2I-VRWKV · UrbanLF-SynmIoU: 83.37 -> 86.46Improved
use MHSA-based EPI geometric prior instead of EPI Bias (ablation)E2I-VRWKV · UrbanLF-SynmIoU: 83.48 -> 86.46Improved
add both VRWKV and EPI Bias (ablation)E2I-VRWKV · UrbanLF-SynmIoU: 80.20 -> 86.46Improved
add Dual-Modal Stream (DMS) rectification (ablation)E2I-VRWKV · UrbanLF-SynmIoU: 85.32 -> 86.46Improved
add Gated Fusion (ablation)E2I-VRWKV · UrbanLF-SynmIoU: 84.98 -> 86.46Improved
use q shift token shift instead of single shift (ablation)E2I-VRWKV · UrbanLF-SynmIoU: 84.69 -> 86.46Improved
use q shift instead of double shift (ablation)E2I-VRWKV · UrbanLF-SynmIoU: 85.78 -> 86.46Improved
scale backbone from MiT-B3 to MiT-B4 (ablation)E2I-VRWKV · UrbanLFmIoU: 83.08 -> 86.46Improved
scale backbone from MiT-B1 to MiT-B4 (ablation)E2I-VRWKV · UrbanLFmIoU: 70.61 -> 86.46Improved
add explicit EPI geometry-aware tokenization to flattened linear baseline (ablation)E2I-VRWKV · UrbanLF-SynBT mIoU: 66.52 -> 83.01Improved
use E2I-VRWKV instead of OAFuserE2I-VRWKV · UrbanLF-Synlatency (ms): 52.4 -> 44.1Improved

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