相关论文: Structured3D: A Large Photo-realistic Dataset for …

We study the problem of synthesizing immersive 3D indoor scenes from one or more images. Our aim is to generate high-resolution images and videos from novel viewpoints, including viewpoints that extrapolate far beyond the input images while…

We present 3DMiner -- a pipeline for mining 3D shapes from challenging large-scale unannotated image datasets. Unlike other unsupervised 3D reconstruction methods, we assume that, within a large-enough dataset, there must exist images of…

Neural rendering techniques promise efficient photo-realistic image synthesis while at the same time providing rich control over scene parameters by learning the physical image formation process. While several supervised methods have been…

Grasping skill is a major ability that a wide number of real-life applications require for robotisation. State-of-the-art robotic grasping methods perform prediction of object grasp locations based on deep neural networks. However, such…

The availability of the large-scale labeled 3D poses in the Human3.6M dataset plays an important role in advancing the algorithms for 3D human pose estimation from a still image. We observe that recent innovation in this area mainly focuses…

Estimating human pose, shape, and motion from images and videos are fundamental challenges with many applications. Recent advances in 2D human pose estimation use large amounts of manually-labeled training data for learning convolutional…

Spatial reasoning is an important component of human intelligence. We can imagine the shapes of 3D objects and reason about their spatial relations by merely looking at their three-view line drawings in 2D, with different levels of…

Humans can naturally identify and mentally complete occluded objects in cluttered environments. However, imparting similar cognitive ability to robotics remains challenging even with advanced reconstruction techniques, which models scenes…

The task of generating natural images from 3D scenes has been a long standing goal in computer graphics. On the other hand, recent developments in deep neural networks allow for trainable models that can produce natural-looking images with…

Surgery monitoring in Mixed Reality (MR) environments has recently received substantial focus due to its importance in image-based decisions, skill assessment, and robot-assisted surgery. Tracking hands and articulated surgical instruments…

Class-agnostic 3D instance segmentation tackles the challenging task of segmenting all object instances, including previously unseen ones, without semantic class reliance. Current methods struggle with generalization due to the scarce…

Reconstructing accurate 3D surfaces for street-view scenarios is crucial for applications such as digital entertainment and autonomous driving simulation. However, existing street-view datasets, including KITTI, Waymo, and nuScenes, only…

We propose a new procedure to guide training of a data-driven shape generative model using a structure-aware loss function. Complex 3D shapes often can be summarized using a coarsely defined structure which is consistent and robust across…

With the recent growth of urban mapping and autonomous driving efforts, there has been an explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color cameras. However, due to high labeling costs, ground-truth…

Recent point-based differentiable rendering techniques have achieved significant success in high-fidelity reconstruction and fast rendering. However, due to the unstructured nature of point-based representations, they are difficult to apply…

Acquiring 3D geometry of real world objects has various applications in 3D digitization, such as navigation and content generation in virtual environments. Image remains one of the most popular media for such visual tasks due to its…

Synthetic images rendered by graphics engines are a promising source for training deep networks. However, it is challenging to ensure that they can help train a network to perform well on real images, because a graphics-based generation…

This work presents a new state of the art in reconstruction of surface realizations from obfuscated text. We identify the lack of sufficient training data as the major obstacle to training high-performing models, and solve this issue by…

Neural networks need big annotated datasets for training. However, manual annotation can be too expensive or even unfeasible for certain tasks, like multi-person 2D pose estimation with severe occlusions. A remedy for this is synthetic data…

We introduce the Reality-linked 3D Scenes (R3DS) dataset of synthetic 3D scenes mirroring the real-world scene arrangements from Matterport3D panoramas. Compared to prior work, R3DS has more complete and densely populated scenes with…