Skip to main content
Search

# SAM3

4 related articles

Subscribe to updates
  1. researchsquare.com

    Copper frame diameters leave the caliper behind: zero-shot segmentation plus adaptive edges hold five new frames to 2.4–6.3 µm

    Diameter inspection of CuCrZr frames for the Beijing Huairou High Energy Photon Source moves to a fully automatic vision pipeline: SAM3 extracts the target region without training, SAM-Canny adaptively picks the dilation kernel and Canny thresholds, and a WOA-RBF network compensates illumination-induced bias from grayscale features of different material regions. On five unseen frames the algorithm held errors to 2.4–6.3 µm, while manual micrometer measurement reached 32.1 µm.

    Institute of High Energy PhysicsBeijing Information Science & Technology University
    yuheng Wang（First author）Yabing Wang（First author）Yuhai Gu（Corresponding author）Weiwei Zhang（Corresponding author）
    SAM-CannySAM3WOA-RBF error compensationCuCrZr frame diameter measurement
  2. Visual Computing for Industry Biomedicine and Art

    Lesion segmentation drops the per-lesion box: one concept prompt lets SAM3 outline 11 lesion types across 13 datasets

    SAM3 segments lesions from text or image-exemplar concept prompts across 13 datasets and 11 lesion types, beating SAM2 on Dice in 10 datasets, by 4.41 on ISLES22 and 5.39 on ISIC2018.

    University of PennsylvaniaSouthwestern Medical CenterThe University of Texas Southwestern Medical Center
    Guoping Xu（First author）You Zhang（Corresponding author）Ying Zhang（Corresponding author）
    SAM3Lesion SegmentationAdapter-based Fine-TuningConcept-Prompt-Based Segmentation
  3. arXiv

    TSegAgent achieves zero-shot tooth segmentation and FDI identification by pairing SAM3 with geometric reasoning, reaching mIoU 93.37 and TIR=1 of 87.17% on Teeth3DS while generalizing to a private dataset

    The work proposes TSegAgent, which reformulates tooth instance segmentation and FDI labeling of intra-oral scanned 3D models as a zero-shot geometric reasoning problem: multi-view renderings with curvature heatmaps and the SAM3 text prompt "tooth" produce candidate masks, which are merged into face-level instance labels via IoU and containment relations, after which a geometry-aware vision-language agent performs non-tooth region identification, central incisor localization, full-arch classification, and error correction through multi-round conversation; it reports mIoU 93.37, TLA 96.40, TSA 96.76, TIR 97.46, and TIR=1 87.17 on Teeth3DS with 1200 3D tooth models, and mIoU 82.10, TLA 96.68, TSA 95.99, TIR 85.41, and TIR=1 51.

    University of SurreyShandong UniversityUniversity of Jinan
    Shaojie Zhuang（First author）Lu Yin（Corresponding author）Yuanfeng Zhou（Corresponding author）
    TSegAgentZero-shot tooth segmentationVision-language agentSAM3Teeth3DS dataset
  4. arXiv

    DA-SAM3 routes over dual-adaptive low-rank experts to gain about 5% accuracy while cutting MoE parameter overhead by over 80% on four public medical segmentation benchmarks

    The work proposes Dual-Adaptive SAM3 (DA-SAM3), which replaces selected feed-forward blocks in SAM3's fusion module with dual-adaptive MoE layers: a task-aware Dynamic Expert Router (DER) sparsely activates experts by jointly reasoning over visual content and the textual concept prompt, while a parameter-aware Decomposed Parameterized Experts (DPE) design represents each expert as a shared frozen base inherited from pretrained SAM3 plus a lightweight trainable low-rank delta, so that on the four public datasets Synapse CT, MMWHS, BTCV and ACDC it matches or exceeds fully fine-tuned SAM3 and standard MoE baselines, reports roughly a 5% gain over then state-of-the-art methods, and reduces MoE parameter overhead by more than 80%.

    Nanyang Technological UniversityImperial College London
    Ying Chen（First author）Qiankun Li（Corresponding author）Kun Wang（Corresponding author）
    Dual-Adaptive SAM3Medical Image SegmentationMixture-of-ExpertsParameter-Efficient Fine-TuningSAM3

You’re all caught up