Related papers: Domain-Adaptive Single-View 3D Reconstruction

Single-view 3D reconstruction is currently approached from two dominant perspectives: reconstruction of scenes with limited diversity using 3D data supervision or reconstruction of diverse singular objects using large image priors. However,…

Modern deep neural networks (DNNs) are highly accurate on many recognition tasks for overhead (e.g., satellite) imagery. However, visual domain shifts (e.g., statistical changes due to geography, sensor, or atmospheric conditions) remain a…

3D Morphable Model (3DMM) fitting has widely benefited face analysis due to its strong 3D priori. However, previous reconstructed 3D faces suffer from degraded visual verisimilitude due to the loss of fine-grained geometry, which is…

Annotating large scale datasets to train modern convolutional neural networks is prohibitively expensive and time-consuming for many real tasks. One alternative is to train the model on labeled synthetic datasets and apply it in the real…

Due to the difficulty of obtaining ground-truth labels, learning from virtual-world datasets is of great interest for real-world applications like semantic segmentation. From domain adaptation perspective, the key challenge is to learn…

A practical shortcoming of deep neural networks is their specialization to a single task and domain. While recent techniques in domain adaptation and multi-domain learning enable the learning of more domain-agnostic features, their success…

3D reconstruction is a longstanding ill-posed problem, which has been explored for decades by the computer vision, computer graphics, and machine learning communities. Since 2015, image-based 3D reconstruction using convolutional neural…

Generating 3D images of complex objects conditionally from a few 2D views is a difficult synthesis problem, compounded by issues such as domain gap and geometric misalignment. For instance, a unified framework such as Generative Adversarial…

Recent work on single-view 3D reconstruction shows impressive results, but has been restricted to a few fixed categories where extensive training data is available. The problem of generalizing these models to new classes with limited…

Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks. Yet, in practice, people, no matter how conscientious, have trouble precisely delineating in 3D and on a large scale, in part…

Deploying machine learning algorithms for robot tasks in real-world applications presents a core challenge: overcoming the domain gap between the training and the deployment environment. This is particularly difficult for visuomotor…

3D Shape representation has substantial effects on 3D shape reconstruction. Primitive-based representations approximate a 3D shape mainly by a set of simple implicit primitives, but the low geometrical complexity of the primitives limits…

Domain shift caused by, e.g., different geographical regions or acquisition conditions is a common issue in machine learning for global scale satellite image processing. A promising method to address this problem is domain adaptation, where…

Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency.However, training deep neural networks typically requires a large volume of data, whereas face images with ground-truth…

Point cloud processing and 3D shape understanding are very challenging tasks for which deep learning techniques have demonstrated great potentials. Still further progresses are essential to allow artificial intelligent agents to interact…

Recovering 3D object pose and shape from a single image is a challenging and ill-posed problem. This is due to strong (self-)occlusions, depth ambiguities, the vast intra- and inter-class shape variance, and the lack of 3D ground truth for…

Estimating the 3D shape of an object using a single image is a difficult problem. Modern approaches achieve good results for general objects, based on real photographs, but worse results on less expressive representations such as historic…

Deep learning-based 3D object detection has achieved unprecedented success with the advent of large-scale autonomous driving datasets. However, drastic performance degradation remains a critical challenge for cross-domain deployment. In…

The well known domain shift issue causes model performance to degrade when deployed to a new target domain with different statistics to training. Domain adaptation techniques alleviate this, but need some instances from the target domain to…

Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques. Owing to the severe spatial occlusion and inherent variance of point density with the distance to…