Rgb T Imaging
PulseAugur coverage of Rgb T Imaging — every cluster mentioning Rgb T Imaging across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New SARTM framework adapts SAM for RGB-thermal segmentation
Researchers have developed SARTM, a new framework designed to adapt the Segment Anything Model (SAM) for RGB-thermal (RGB-T) semantic segmentation. SARTM fine-tunes SAM with LoRA layers and incorporates language guidanc…
-
New S3AM framework enhances multi-modal salient object detection
Researchers have developed S$^3$AM, a novel single-stream framework for multi-modal salient object detection. This approach integrates a reliability-calibrated frequency adapter with the Segment Anything Model (SAM) bac…
-
New FOCUS framework boosts MLLM salient object detection capabilities
A new research paper proposes FOCUS, a novel framework designed to enhance salient object detection (SOD) capabilities in multimodal large language models (MLLMs). The paper introduces SaliLLM, a diagnostic benchmark th…
-
New RGB-T object detection method boosts efficiency with sparse fusion
Researchers have developed a novel approach to RGB-T object detection that significantly improves efficiency by employing a sparse cross-modality fusion mechanism. This method first rapidly identifies potential object r…
-
DarkVGGT framework uses thermal imaging for 3D reconstruction in darkness
Researchers have developed DarkVGGT, a new framework designed for 3D scene geometry estimation in low-light conditions. This system leverages both RGB and thermal imaging, incorporating physics-aware thermal modeling to…
-
Physical Adversarial Clothing Evades Visible-Thermal Detectors via Non-Overlapping RGB-T Pattern
Researchers have developed a novel method for physical adversarial attacks against visible-thermal (RGB-T) object detectors, commonly used in applications like autonomous driving. The approach utilizes specially designe…
-
RACANet improves RGB-T crowd counting with reliability-aware fusion
Researchers have developed RACANet, a novel framework for RGB-Thermal crowd counting that improves accuracy by explicitly modeling local spatial discrepancies and modality reliability. The method employs a two-stage app…