Shadow boundaries can be confused with material boundaries as both exhibit sharp changes in luminance or contrast within a scene. However, shadows do not modify the intrinsic color or texture of surfaces. Therefore, on both sides of shadow edges traversing regions with the same material, the original color and texture should be the same if the shadow is removed properly. These shadow/shadow-free pairs are very useful but difficult-to-collect supervision signals. The crucial contribution of this paper is to learn how to identify those shadow edges that traverse material-consistent regions and how to use them as self-supervision for shadow removal refinement during test time. To achieve this, we fine-tune SAM, an image segmentation foundation model, to produce a shadow-invariant segmentation and then extract material-consistent shadow edges by comparing the SAM segmentation with the shadow mask. Utilizing these shadow edges, we in-troduce color- and texture-consistency losses to enhance the shadow removal process. We demonstrate the effectiveness of our method in improving shadow removal results on more challenging, in-the-wild images, outperforming the state-of-the-art shadow removal methods. Addition-ally, we propose a new metric and an annotated dataset for evaluating the performance of shadow removal methods without the need for paired shadow/shadow-free data. Our code and dataset are available at: https://github.com/cvlab-stonybrook/ShadowRemovalRefine

Document unwarping attempts to undo physical deformations of the paper and recover a ’flatbed’ scanned document-image for downstream tasks such as OCR. Current state-of-the-art relies on global unwarping of the document which is not robust to local deformation changes. Moreover, a global unwarping often produces spurious warping artifacts in less warped regions to compensate for severe warps present in other parts of the document. In this paper, we propose the first end-to-end trainable piece-wise unwarping1method that predicts local deformation fields and stitches them together with global information to obtain an improved unwarping. The proposed piece-wise formulation results in 4% improvement in terms of multi-scale structural similarity (MS-SSIM) and shows better performance in terms of OCR metrics, character error rate (CER) and word error rate (WER) compared to the state-of-the-art.

Fluent and confident speech is desirable to every speaker. But professional speech delivering requires a great deal of experience and practice. In this paper, we propose a speech stream manipulation system which can help non-professional speakers to produce fluent, professional-like speech content, in turn contributing towards better listener engagement and comprehension. We propose to achieve this task by manipulating the disfluencies in human speech, like the sounds uh and um, the filler words and awkward long silences. Given any unrehearsed speech we segment and silence the filled pauses and doctor the duration of imposed silence as well as other long pauses (disfluent) by a predictive model learned using professional speech dataset. Finally, we output a audio stream in which speaker sounds more fluent, confident and practiced compared to the original recorded speech. According to our quantitative evaluation, we significantly increase the fluency of speech by reducing rate of pauses and fillers.

Capturing document images with hand-held devices in unstructured environments is a common practice nowadays. However, "casual" photos of documents are usually unsuitable for automatic information extraction, mainly due to physical distortion of the document paper, as well as various camera positions and illumination conditions. In this work, we propose DewarpNet, a deep-learning approach for document image unwarping from a single image. Our insight is that the 3D geometry of the document not only determines the warping of its texture but also causes the illumination effects. Therefore, our novelty resides on the explicit modeling of 3D shape for document paper in an end-to-end pipeline. Also, we contribute the largest and most comprehensive dataset for document image unwarping to date - Doc3D. This dataset features multiple ground-truth annotations, including 3D shape, surface normals, UV map, albedo image, etc. Training with Doc3D, we demonstrate state-of-the-art performance for DewarpNet with extensive qualitative and quantitative evaluations. Our network also significantly improves OCR performance on captured document images, decreasing character error rate by 42% on average. Both the code and the dataset are released.

Handheld cameras are currently the device of choice for performing document digitization, due to their convenience, ubiquity and high performance at low cost. Software methods process a captured image, to rectify distortions and reconstruct the original document. Existing methods struggle to reconstruct a flattened version given a single image of a document distorted by folding. We propose a novel non-parametric page dewarping approach from a single image based on deep learning to identify creases due to folds on the paper. Our method then performs a 2D boundary method based on polynomial regression, and a Coons patch, to get a flattened reconstruction. We found our method improves OCR word accuracy by more than 2.5 times when compared to the original distorted image.