Search Results for author:
Found 11 papers, 2 papers with code
From Posterior Sampling to Meaningful Diversity in Image Restoration
To accommodate this, many works generate a diverse set of outputs by attempting to randomly sample from the posterior distribution of natural images given the degraded input.
Neural Volume Super-Resolution
This allows us to super-resolve the 3D scene representation by applying 2D convolutional networks on the 2D feature planes.
Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions
Probabilistic diffusion models have achieved state-of-the-art results for image synthesis, inpainting, and text-to-image tasks.
Neural Point Light Fields
We introduce Neural Point Light Fields that represent scenes implicitly with a light field living on a sparse point cloud.
Deep Self-Dissimilarities as Powerful Visual Fingerprints
Features extracted from deep layers of classification networks are widely used as image descriptors.
Classification Confidence Estimation with Test-Time Data-Augmentation
This suggests the task of detecting errors, which we tackle in this paper for the case of visual classification.
What's in the Image? Explorable Decoding of Compressed Images
In spite of this fact, existing decompression algorithms typically produce only a single output, and do not allow the viewer to explore the set of images that map to the given compressed code.
Explorable Super Resolution
Single image super resolution (SR) has seen major performance leaps in recent years.
Natural and Adversarial Error Detection using Invariance to Image Transformations
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.).
Confidence from Invariance to Image Transformations
We develop a technique for automatically detecting the classification errors of a pre-trained visual classifier.
Non-Uniform Blind Deblurring by Reblurring
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.
