Confocal endomicroscopy provides tools for in vivo imaging of human cell architecture endoscopically. These technologies are a tough challenge since multiple trade-offs have to be overcome: resolution versus field of view, dynamic versus stability, contrast versus low laser power or low contrast agent doses. Many difficult clinical applications, such as lung, bile duct, urethral imaging and NOTES applications, need to optimize miniaturization, resolution, frame rate and contrast agent dose simultaneously. We propose one solution based on real-time video image processing to efficiently address these trade-offs. Dynamic imaging provides a flow of images that we process in real time. Images are aligned using efficientalgorithms specifically adapted to confocal devices. From the displacement that we find across the images, instantaneous velocities are computed and used to compensate for motion distortions. All images are stitched together onto the same reference space and displayed in real-time to reconstruct an image of the entire surface explored during the clinical procedure. This representation brings both stability and an increased field of view. Moreover, because a given area can be imaged by several frames, the contrast can be improved using temporal adaptive averaging. Such processing enhances the visualization of the video sequence, overcoming most classical trade-offs. The stability and increased field of view help the clinician better focus his attention on his practice which improves the patient benefit. Our tools are currently evaluated in a multicenter clinical trial to assess the improvement of the clinical practice.