Probabilistic diffusion models have achieved state-of-the-art results for image synthesis, inpainting and text-to-image tasks. However, they are still in the early stages of generating complex 3D shapes. This work proposes Diffusion-SDF, a generative model for shape completion, single-view reconstruction and reconstruction of real-scanned point clouds. We use neural signed distance functions (SDFs) as our 3D representation to parameterize the geometry of various signals (e.g., point clouds, 2D images) through neural networks. Neural SDFs are implicit functions and diffusing them amounts to learning the reversal of their neural network weights, which we solve using a custom modulation module. Extensive experiments show that our method is capable of both realistic unconditional generation and conditional generation from partial inputs. This work expands the domain of diffusion models from learning 2D, explicit representations, to 3D, implicit representations.

We introduce Neural Point Light Fields that represent scenes implicitly with a light field living on a sparse point cloud. Combining differentiable volume rendering with learned implicit density representations has made it possible to synthesize photo-realistic images for novel views of small scenes. As neural volumetric rendering methods require dense sampling of the underlying functional scene representation, at hundreds of samples along a ray cast through the volume, they are fundamentally limited to small scenes with the same objects projected to hundreds of training views. Promoting sparse point clouds to neural implicit light fields allows us to represent large scenes effectively with only a single implicit sampling operation per ray. These point light fields are as a function of the ray direction, and local point feature neighborhood, allowing us to interpolate the light field conditioned training images without dense object coverage and parallax. We assess the proposed method for novel view synthesis on large driving scenarios, where we synthesize realistic unseen views that existing implicit approaches fail to represent. We validate that Neural Point Light Fields make it possible to predict videos along unseen trajectories previously only feasible to generate by explicitly modeling the scene.

Single image super resolution (SR) has seen major performance leaps in recent years. However, existing methods do not allow exploring the infinitely many plausible reconstructions that might have given rise to the observed low-resolution (LR) image. These different explanations to the LR image may dramatically vary in their textures and fine details, and may often encode completely different semantic information. In this paper, we introduce the task of explorable super resolution. We propose a framework comprising a graphical user interface with a neural network backend, allowing editing the SR output so as to explore the abundance of plausible HR explanations to the LR input. At the heart of our method is a novel module that can wrap any existing SR network, analytically guaranteeing that its SR outputs would precisely match the LR input, when downsampled. Besides its importance in our setting, this module is guaranteed to decrease the reconstruction error of any SR network it wraps, and can be used to cope with blur kernels that are different from the one the network was trained for. We illustrate our approach in a variety of use cases, ranging from medical imaging and forensics, to graphics.

We propose an approach to distinguish between correct and incorrect image classifications. Our approach can detect misclassifications which either occur unintentionally (``natural errors''), or due to intentional adversarial attacks (``adversarial errors''), both in a single unified framework. Our approach is based on the observation that correctly classified images tend to exhibit robust and consistent classifications under certain image transformations (e.g., horizontal flip, small image translation, etc.). In contrast, incorrectly classified images (whether due to adversarial errors or natural errors) tend to exhibit large variations in classification results under such transformations. Our approach does not require any modifications or retraining of the classifier, hence can be applied to any pre-trained classifier. We further use state of the art targeted adversarial attacks to demonstrate that even when the adversary has full knowledge of our method, the adversarial distortion needed for bypassing our detector is no longer imperceptible to the human eye. Our approach obtains state-of-the-art results compared to previous adversarial detection methods, surpassing them by a large margin.

We present an approach for blind image deblurring, which handles non-uniform blurs. Our algorithm has two main components: (i) A new method for recovering the unknown blur-field directly from the blurry image, and (ii) A method for deblurring the image given the recovered nonuniform blur-field. Our blur-field estimation is based on simple spectral analysis of blurry image patches. Being unrestricted by any training data, it can handle a large variety of blur sizes, yielding superior blur-field estimation results compared to training-based deep-learning methods. Our non-uniform deblurring algorithm is based on the internal image-specific patch-recurrence prior. It attempts to recover a sharp image which, on one hand – results in the blurry image under our estimated blur-field, and on the other hand – maximizes the internal recurrence of patches within and across scales of the recovered sharp image. The combination of these two components gives rise to a blinddeblurring algorithm, which exceeds the performance of state-of-the-art CNN-based blind-deblurring by a significant margin, without the need for any training data.

The popularity of voice over internet protocol (VoIP) systems is continuously growing. Such systems depend on unreliable internet communication, in which chunks of data often get lost during transmission. Various solutions to this problem were proposed, most of which are better suited to small rates of lost data. This work addresses this problem by filling in missing data using examples taken from prior recorded audio of the same user. Our approach also harnesses statistical priors and data inpainting smoothing techniques. The effectiveness of the proposed solution is demonstrated experimentally, even in large data-gaps, which cannot be handled by standard packet loss concealment techniques.