Related papers: Sat2Density: Faithful Density Learning from Satell…
With the growing demand for high-fidelity 3D models from 2D images, existing methods still face significant challenges in accurately reproducing fine-grained geometric details due to limitations in domain gaps and inherent ambiguities in…
With the development of remote sensing technology in recent decades, spaceborne sensors with sub-meter and meter spatial resolution (Worldview and PlanetScope) have achieved a considerable image quality to generate 3D geospatial data via a…
Since the advent of Neural Radiance Fields, novel view synthesis has received tremendous attention. The existing approach for the generalization of radiance field reconstruction primarily constructs an encoding volume from nearby source…
Three-dimensional (3D) urban models have gained interest because of their applications in many use-cases such as urban planning and virtual reality. However, generating these 3D representations requires LiDAR data, which are not always…
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…
Depth completion, aiming to predict dense depth maps from sparse depth measurements, plays a crucial role in many computer vision related applications. Deep learning approaches have demonstrated overwhelming success in this task. However,…
We introduce a novel learning-based method to reconstruct the high-quality geometry and complex, spatially-varying BRDF of an arbitrary object from a sparse set of only six images captured by wide-baseline cameras under collocated point…
We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views. Previous work on learning shape reconstruction from multiple views uses discrete…
In this work, we focus on synthesizing high-fidelity novel view images for arbitrary human performers, given a set of sparse multi-view images. It is a challenging task due to the large variation among articulated body poses and heavy…
Nowadays the accurate geo-localization of ground-view images has an important role across domains as diverse as journalism, forensics analysis, transports, and Earth Observation. This work addresses the problem of matching a query…
Recently multi-view crowd counting using deep neural networks has been proposed to enable counting in large and wide scenes using multiple cameras. The current methods project the camera-view features to the average-height plane of the 3D…
Modern 3D computer vision leverages learning to boost geometric reasoning, mapping image data to classical structures such as cost volumes or epipolar constraints to improve matching. These architectures are specialized according to the…
We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of…
3D Gaussian Splatting (3DGS) has emerged as a novel paradigm for 3D reconstruction from satellite imagery. However, in multi-temporal satellite images, prevalent shadows exhibit significant inconsistencies due to varying illumination…
We present a method that simultaneously addresses the tasks of dynamic scene novel-view synthesis and six degree-of-freedom (6-DOF) tracking of all dense scene elements. We follow an analysis-by-synthesis framework, inspired by recent work…
Deep learning models in the Earth Observation domain heavily rely on the availability of large-scale accurately labeled satellite imagery. However, obtaining and labeling satellite imagery is a resource-intensive endeavor. While generative…
Recently, building on the foundation of neural radiance field, various techniques have emerged to learn unsigned distance fields (UDF) to reconstruct 3D non-watertight models from multi-view images. Yet, a central challenge in UDF-based…
Synthesizing accurate geometry and photo-realistic appearance of small scenes is an active area of research with compelling use cases in gaming, virtual reality, robotic-manipulation, autonomous driving, convenient product capture, and…
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…
Current methods for single-image depth estimation use training datasets with real image-depth pairs or stereo pairs, which are not easy to acquire. We propose a framework, trained on synthetic image-depth pairs and unpaired real images,…