# SHED Light on Segmentation for Dense Prediction Source: [SHED Light on Segmentation for Dense Prediction]() Collection index: [llms.txt]() Data updated: 2026-02-03T05:00:04.373Z Authors: Seung Hyun Lee, Sangwoo Mo, Stella X. Yu Published: 2026-01-30T04:02:29.000Z ## Abstract Dense prediction infers per-pixel values from a single image and is fundamental to 3D perception and robotics. Although real-world scenes exhibit strong structure, existing methods treat it as an independent pixel-wise prediction, often resulting in structural inconsistencies. We propose SHED, a novel encoder-decoder architecture that enforces geometric prior explicitly by incorporating segmentation into dense prediction. By bidirectional hierarchical reasoning, segment tokens are hierarchically pooled in the encoder and unpooled in the decoder to reverse the hierarchy. The model is supervised only at the final output, allowing the segment hierarchy to emerge without explicit segmentation supervision. SHED improves depth boundary sharpness and segment coherence, while demonstrating strong cross-domain generalization from synthetic to the real-world environments. Its hierarchy-aware decoder better captures global 3D scene layouts, leading to improved semantic segmentation performance. Moreover, SHED enhances 3D reconstruction quality and reveals interpretable part-level structures that are often missed by conventional pixel-wise methods. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Depth Estimation on SUN-RGBD (AbsRel and Delta \> 1.25 Threshold)](): Depth Estimation; SUN-RGBD; AbsRel: 7.16. - [Monocular Depth Estimation on NYU v2 (test)](): Monocular Depth Estimation; NYU v2 (test); Abs Rel: 0.123. - [Semantic Segmentation on ADE20K](): Semantic segmentation; ADE20K; mIoU: 44.5. - [Depth Estimation on NYU Depth v2](): Depth Estimation; NYU Depth V2; RMSE: not recorded. - [Depth Estimation on KITTI](): Depth Estimation; KITTI; RMSE: not recorded. ## Original sources and implementation [Original paper]() [PDF]()