AI Paper Atlas

Research map / 3D vision / 3D generation

SAM+D: Parameter-Efficient Dimensional Lifting of SAM-Family Models via Depth-Routed LoRA and Depth Shifting

YU SONG, Hao Sun, TENG SHIYU, Ikuko Nishikawa, Yen-wei Chen

ECCV 2026 · 3D vision › 3D generation · approach: 2D-to-3D pretrained representations · 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 Depth Shift Module to DRLoRA (ablation)SAM+D · LiTSDice (%): 56.41 -> 59.17Improved
add depth embedding (z-embed) (ablation)SAM+D · LiTSDice (%): 59.17 -> 61.05Improved
add LoRA in the mask decoder (ablation)SAM+D · LiTSDice (%): 61.05 -> 63.33Improved
use 4 depth-routed experts instead of a single LoRA (ablation)SAM+D · LiTSDice (%): 58.86 -> 63.33Improved
increase experts from 4 to 8 (ablation)SAM+D · LiTSDice (%): 63.33 -> 63.10No clear effect
set DSM shift ratio to 0.25 instead of 0.125 (ablation)SAM+D · LiTSDice (%): 61.22 -> 63.33Improved
set DSM shift ratio to 0.25 instead of 0.5 (ablation)SAM+D · LiTSDice (%): 62.08 -> 63.33Improved
use LoRA rank 16 instead of 4 (ablation)SAM+D · LiTSDice (%): 60.72 -> 63.33Improved
use LoRA rank 16 instead of 32 (ablation)SAM+D · LiTSDice (%): 62.19 -> 63.33Improved
use DSM instead of cross-slice attention (ablation)SAM+D · LiTSDice (%): 55.01 -> 63.33Improved
use DSM instead of Conv3D adapter (ablation)SAM+D · LiTSDice (%): 53.62 -> 63.33Improved
use depth routing instead of content-based MoLoRA routing (ablation)SAM+D · LiTSDice (%): 55.47 -> 63.33Improved

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