Related papers: Opening the Black Box of 3D Reconstruction Error A…
Scientific imaging techniques such as optical and electron microscopy and computed tomography (CT) scanning are used to study the 3D structure of an object through 2D observations. These observations are related to the original 3D object…
We present an approach for the planar surface reconstruction of a scene from images with limited overlap. This reconstruction task is challenging since it requires jointly reasoning about single image 3D reconstruction, correspondence…
Autonomous aerial robots are increasingly being deployed in real-world scenarios, where transparent obstacles present significant challenges to reliable navigation and mapping. These materials pose a unique problem for traditional…
Robot-guided catheter insertion has the potential to deliver urgent medical care in situations where medical personnel are unavailable. However, this technique requires accurate and reliable segmentation of anatomical landmarks in the body.…
In this work we address the challenging problem of multiview 3D surface reconstruction. We introduce a neural network architecture that simultaneously learns the unknown geometry, camera parameters, and a neural renderer that approximates…
Active vision (AV) has been in the spotlight of robotics research due to its emergence in numerous applications including agricultural tasks such as precision crop monitoring and autonomous harvesting to list a few. A major AV problem that…
Deep learning applied to the reconstruction of 3D shapes has seen growing interest. A popular approach to 3D reconstruction and generation in recent years has been the CNN encoder-decoder model usually applied in voxel space. However, this…
We introduce a framework for multi-camera 3D object detection. In contrast to existing works, which estimate 3D bounding boxes directly from monocular images or use depth prediction networks to generate input for 3D object detection from 2D…
Light spectra are a very important source of information for diverse classification problems, e.g., for discrimination of materials. To lower the cost for acquiring this information, multispectral cameras are used. Several techniques exist…
Robotic-assisted surgery allows surgeons to conduct precise surgical operations with stereo vision and flexible motor control. However, the lack of 3D spatial perception limits situational awareness during procedures and hinders mastering…
Mobile robots operating indoors must be prepared to navigate challenging scenes that contain transparent surfaces. This paper proposes a novel method for the fusion of acoustic and visual sensing modalities through implicit neural…
3D dense reconstruction refers to the process of obtaining the complete shape and texture features of 3D objects from 2D planar images. 3D reconstruction is an important and extensively studied problem, but it is far from being solved. This…
Objects manipulated by the hand (i.e., manipulanda) are particularly challenging to reconstruct from Internet videos. Not only does the hand occlude much of the object, but also the object is often only visible in a small number of image…
Object shape provides important information for robotic manipulation; for instance, selecting an effective grasp depends on both the global and local shape of the object of interest, while reaching into clutter requires accurate surface…
This paper is about reducing the cost of building good large-scale 3D reconstructions post-hoc. We render 2D views of an existing reconstruction and train a convolutional neural network (CNN) that refines inverse-depth to match a…
To translate synthetic aperture radar (SAR) image into interpretable forms for human understanding is the ultimate goal of SAR advanced information retrieval. Existing methods mainly focus on 3D surface reconstruction or local geometric…
Given a monocular video, the goal of video re-rendering is to generate views of the scene from a novel camera trajectory. Existing methods face two distinct challenges. Geometrically unconditioned models lack spatial awareness, leading to…
Lorentz Transmission Electron Microscopy (TEM) observations of magnetic nanoparticles contain information on the magnetic and electrostatic potentials. Vector Field Electron Tomography (VFET) can be used to reconstruct electromagnetic…
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…
Current evaluations of spatial intelligence can be systematically invalid under modern vision-language model (VLM) settings. First, many benchmarks derive question-answer (QA) pairs from point-cloud-based 3D annotations originally curated…