1,721,003 research outputs found
Merging and Splitting Diffusion Paths for Semantically Coherent Panoramas
No full textDiffusion models have become the State-of-the-Art for text-to-image generation, and increasing research effort has been dedicated to adapting the inference process of pretrained diffusion models to achieve zero-shot capabilities. An example is the generation of panorama images, which has been tackled in recent works by combining independent diffusion paths over overlapping latent features, which is referred to as joint diffusion, obtaining perceptually aligned panoramas. However, these methods often yield semantically incoherent outputs and trade-off diversity for uniformity. To overcome this limitation, we propose the Merge-Attend-Diffuse operator, which can be plugged into different types of pretrained diffusion models used in a joint diffusion setting to improve the perceptual and semantical coherence of the generated panorama images. Specifically, we merge the diffusion paths, reprogramming self- and cross-attention to operate on the aggregated latent space. Extensive quantitative and qualitative experimental analysis, together with a user study, demonstrate that our method maintains compatibility with the input prompt and visual quality of the generated images while increasing their semantic coherence. We release the code at https://github.com/aimagelab/MAD
Binarizing Documents by Leveraging both Space and Frequency
No full textDocument Image Binarization is a well-known problem in Document Analysis and Computer Vision, although it is far from being solved. One of the main challenges of this task is that documents generally exhibit degradations and acquisition artifacts that can greatly vary throughout the page. Nonetheless, even when dealing with a local patch of the document, taking into account the overall appearance of a wide portion of the page can ease the prediction by enriching it with semantic information on the ink and background conditions. In this respect, approaches able to model both local and global information have been proven suitable for this task. In particular, recent applications of Vision Transformer (ViT)-based models, able to model short and long-range dependencies via the attention mechanism, have demonstrated their superiority over standard Convolution-based models, which instead struggle to model global dependencies. In this work, we propose an alternative solution based on the recently introduced Fast Fourier Convolutions, which overcomes the limitation of standard convolutions in modeling global information while requiring fewer parameters than ViTs. We validate the effectiveness of our approach via extensive experimental analysis considering different types of degradations
Preliminary experience in the arthroscopically assisted treatment of tibial plateau fractures
No full textBackground and aim of the study: Fractures involving the tibial plateau make up 1% of all fractures. Treatment can take advantage of various techniques, including arthroscopically assisted surgical reduction. This procedure is certainly viable for Schatzker III fractures and, in some cases, for Schatzker II. The use of the arthroscope makes possible a smooth reduction of the fractured bone, decreasing the risk of post-traumatic osteoarthritis, and also allows to diagnose and, if necessary, also treat the associated intra-articular lesions, which often are not highlighted during the classical preoperative investigations. Methods: In the last year we have operated with this technique 8 of the 22 cases of fracture of the tibial plate that have come to our emergency Department. Using the Schaztker classification, we performed an arthroscopically assisted reduction to treat type II and III fractures. The surgical operations involved a first arthroscopic phase, to assess intrarticular damage (bone, cartilage, ACL, PCL, menisci), a second phase for possible treatment of intrarticular lesions and reduction of fractures under arthroscope or open osteosinthesis. Finally, a last arthroscopic check was performed. Results: We obtained excellent results, as we were able to always have a fracture reduction of less than 1 mm, while clinically all the patients could have an early and almost complete functional recovery after only 2 months. Conclusion: The arthroscopically assisted technique could be an effective way to adress the anatomical reduction of tibial plate fractures, but must only be used in the indicated cases
Treatment of femoral diaphyseal non-unions: Our experience
No full textDespite the continuous advances of surgical solutions, still 1-7% of fractures develop non-unions. The delays in fracture healing increase the period of incapacity of the patient with major consequences, on the psychological and functional recovery, but also on the direct and indirect health-related costs. In particular, femoral diaphyseal non-unions are often characterised by a challenging and long-lasting period of healing. The clinician treating these complex cases has to consider amongst other parameters, the condition of the soft tissue envelope, the adequacy of any pre-existing fixation, the alignment and length of the affected limb, the potential presence of an infection, as well as the general condition of the patient. Open reduction and plate fixation of femoral diaphyseal non-unions offers a valid alternative of stabilisation and if applied to carefully selected cases, can give optimal results
Lo Sport praticato dai disabili con patologia locomotoria è in grado di determinare effetti benefici sulla salute?
No full textVolumetric Fast Fourier Convolution for Detecting Ink on the Carbonized Herculaneum Papyri
No full textRecent advancements in Digital Document Restoration (DDR) have led to significant breakthroughs in analyzing highly damaged written artifacts. Among those, there has been an increasing interest in applying Artificial Intelligence techniques for virtually unwrapping and automatically detecting ink on the Herculaneum papyri collection. This collection consists of carbonized scrolls and fragments of documents, which have been digitized via X-ray tomography to allow the development of ad-hoc deep learning-based DDR solutions. In this work, we propose a modification of the Fast Fourier Convolution operator for volumetric data and apply it in a segmentation architecture for ink detection on the challenging Herculaneum papyri, demonstrating its suitability via deep experimental analysis. To encourage the research on this task and the application of the proposed operator to other tasks involving volumetric data, we will release our implementation (https://github.com/aimagelab/vffc)
Rehabilitation outcome domains following rotator cuff surgical repair: A systematic review
No full text
Treatment of femoral diaphyseal non-unions: our experience
Full text linkDespite the continuous advances of surgical solutions, still 1–7% of fractures develop non-unions. The
delays in fracture healing increase the period of incapacity of the patient with major consequences, on
the psychological and functional recovery, but also on the direct and indirect health-related costs.
In particular, femoral diaphyseal non-unions are often characterised by a challenging and long-lasting
period of healing. The clinician treating these complex cases has to consider amongst other parameters,
the condition of the soft tissue envelope, the adequacy of any pre-existing fixation, the alignment and
length of the affected limb, the potential presence of an infection, as well as the general condition of the
patient.
Open reduction and plate fixation of femoral diaphyseal non-unions offers a valid alternative of
stabilisation and if applied to carefully selected cases, can give optimal results
- …
