Related papers: Style Agnostic 3D Reconstruction via Adversarial S…
We investigate the problem of learning a probabilistic distribution over three-dimensional shapes given two-dimensional views of multiple objects taken from unknown viewpoints. Our approach called projective generative adversarial network…
Learning to transfer visual attributes requires supervision dataset. Corresponding images with varying attribute values with the same identity are required for learning the transfer function. This largely limits their applications, because…
Inferring 3D structure of a generic object from a 2D image is a long-standing objective of computer vision. Conventional approaches either learn completely from CAD-generated synthetic data, which have difficulty in inference from real…
Differentiable rendering is a technique to connect 3D scenes with corresponding 2D images. Since it is differentiable, processes during image formation can be learned. Previous approaches to differentiable rendering focus on mesh-based…
We present a novel 3D pose refinement approach based on differentiable rendering for objects of arbitrary categories in the wild. In contrast to previous methods, we make two main contributions: First, instead of comparing real-world images…
From a single image, humans are able to perceive the full 3D shape of an object by exploiting learned shape priors from everyday life. Contemporary single-image 3D reconstruction algorithms aim to solve this task in a similar fashion, but…
In this paper we present, to the best of our knowledge, the first method to learn a generative model of 3D shapes from natural images in a fully unsupervised way. For example, we do not use any ground truth 3D or 2D annotations, stereo…
We propose a fast feed-forward network for arbitrary style transfer, which can generate stylized image for previously unseen content and style image pairs. Besides the traditional content and style representation based on deep features and…
Understanding the 3D world is a fundamental problem in computer vision. However, learning a good representation of 3D objects is still an open problem due to the high dimensionality of the data and many factors of variation involved. In…
We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We observe that dynamic movement of an object through an environment provides important cues about its objectness,…
3D geometry is a very informative cue when interacting with and navigating an environment. This writing proposes a new approach to 3D reconstruction and scene understanding, which implicitly learns 3D geometry from depth maps pairing a deep…
We propose a novel framework for fine-grained object recognition that learns to recover object variation in 3D space from a single image, trained on an image collection without using any ground-truth 3D annotation. We accomplish this by…
Reconstructing object geometry and material from multiple views typically requires optimization. Differentiable path tracing is an appealing framework as it can reproduce complex appearance effects. However, it is difficult to use due to…
Image to image translation is the problem of transferring an image from a source domain to a different (but related) target domain. We present a new unsupervised image to image translation technique that leverages the underlying semantic…
We present a novel convolutional neural network architecture for photometric stereo (Woodham, 1980), a problem of recovering 3D object surface normals from multiple images observed under varying illuminations. Despite its long history in…
This study aims to learn a translation from visible to infrared imagery, bridging the domain gap between the two modalities so as to improve accuracy on downstream tasks including object detection. Previous approaches attempt to perform…
Object detection networks have reached an impressive performance level, yet a lack of suitable data in specific applications often limits it in practice. Typically, additional data sources are utilized to support the training task. In…
In this work, we tackle the challenging problem of arbitrary image style transfer using a novel style feature representation learning method. A suitable style representation, as a key component in image stylization tasks, is essential to…
With a good image understanding capability, can we manipulate the images high level semantic representation? Such transformation operation can be used to generate or retrieve similar images but with a desired modification (for example…
We present a method to learn single-view reconstruction of the 3D shape, pose, and texture of objects from categorized natural images in a self-supervised manner. Since this is a severely ill-posed problem, carefully designing a training…