R2VD redefines reconstruction as the origin for residual-guided vector diffusion across PPE, GMP, RSM, and VDI stages to achieve superior anomaly detectability and background suppression on eight datasets.
ASTRA: Let Arbitrary Subjects Transform in Video Editing
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
While existing video editing methods excel with single subjects, they struggle in dense, multi-subject scenes, frequently suffering from attention dilution and mask boundary entanglement that cause attribute leakage and temporal instability. To address this, we propose ASTRA, a training-free framework for seamless, arbitrary-subject video editing. Without requiring model fine-tuning, ASTRA precisely manipulates multiple designated subjects while strictly preserving non-target regions. It achieves this via two core components: a prompt-guided multimodal alignment module that generates robust conditions to mitigate attention dilution, and a prior-based mask retargeting module that produces temporally coherent mask sequences to resolve boundary entanglement. Functioning as a versatile plug-and-play module, ASTRA seamlessly integrates with diverse mask-driven video generators. Extensive experiments on our newly constructed benchmark, MSVBench, demonstrate that ASTRA consistently outperforms state-of-the-art methods. Code, models, and data are available at https://github.com/XWH-A/ASTRA.
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 5years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
SARES-DEIM achieves 76.4% mAP50:95 and 93.8% mAP50 on HRSID by routing SAR features through sparse frequency and wavelet experts plus a high-resolution preservation neck, outperforming prior YOLO and SAR detectors.
Proposes orthogonal LoRA banks and novelty-driven bank growth to preserve historical normality priors in continual diffusion-based anomaly detection, reporting 3.2-point pixel A-AUROC gains on VisA 2x6.
WILD-SAM is a fine-tuned SAM variant using phase-aware MoE adapters and wavelet subband enhancement that achieves state-of-the-art landslide detection on wrapped InSAR data.
IB-HFN introduces a dual-stream backbone with spatial information bottleneck fusion, local-global gating, and joint optimization to achieve superior structural and spectral fidelity in SAR-assisted optical cloud removal on the SEN12MS-CR dataset.
citing papers explorer
-
Beyond Reconstruction: Reconstruction-to-Vector Diffusion for Hyperspectral Anomaly Detection
R2VD redefines reconstruction as the origin for residual-guided vector diffusion across PPE, GMP, RSM, and VDI stages to achieve superior anomaly detectability and background suppression on eight datasets.
-
SARES-DEIM: Sparse Mixture-of-Experts Meets DETR for Robust SAR Ship Detection
SARES-DEIM achieves 76.4% mAP50:95 and 93.8% mAP50 on HRSID by routing SAR features through sparse frequency and wavelet experts plus a high-resolution preservation neck, outperforming prior YOLO and SAR detectors.
-
Normality-Preserving Continual Industrial Anomaly Detection via Orthogonal LoRA Banks
Proposes orthogonal LoRA banks and novelty-driven bank growth to preserve historical normality priors in continual diffusion-based anomaly detection, reporting 3.2-point pixel A-AUROC gains on VisA 2x6.
-
WILD-SAM: Phase-Aware Expert Adaptation of SAM for Landslide Detection in Wrapped InSAR Interferograms
WILD-SAM is a fine-tuned SAM variant using phase-aware MoE adapters and wavelet subband enhancement that achieves state-of-the-art landslide detection on wrapped InSAR data.
-
IB-HFN: Information Bottleneck-Driven SAR-Optical Fusion Network for High-Fidelity Cloud Removal
IB-HFN introduces a dual-stream backbone with spatial information bottleneck fusion, local-global gating, and joint optimization to achieve superior structural and spectral fidelity in SAR-assisted optical cloud removal on the SEN12MS-CR dataset.