Search Results

Water and light interactions cause color shifts and blurring in underwater images, while dynamic underwater illumination further disrupts scene consistency, resulting in poor performance of optical image-based reconstruction methods underwater. ...

Display Omitted

• We propose SP-SeaNeRF, a novel neural radiance field for underwater scenes.
• We propose a method to enhance the model’s scattering perception ability.
• We addressed artifacts and floaters caused by dynamic lighting underwater.
• We ...

An overarching goal for computer-aided perception systems is the holistic understanding of the human-centric 3D world, including faithful reconstructions of humans, scenes, and their global spatial relationships. While recent progress in monocular ...

The Neural Radiance Field (NeRF) exhibits excellent performance for view synthesis tasks, but it requires a large amount of memory and model parameters during three-dimensional (3D) scene reconstruction. This paper proposes a block-term tensor ...

Neural rendering has garnered substantial attention owing to its capacity for creating realistic 3D scenes. However, its applicability to extensive scenes remains challenging, with limitations in effectiveness. In this work, we propose the Drone-...

• Propose a novel neural radiance fields framework for drone view reconstruction.
• Parallel sub-block training achieves fast convergence and optimization.
• Merge sub-blocks for large scenes and refine bounds to reduce edge shadows.

In this study, we propose an iterative approach to perform pseudo-scene reconstruction based on multi-focus images for estimating the 4D light fields of the scene robustly. An analogous scene-independent linear filtering approach has ...

We propose an efficient and GPU-accelerated sampling framework which enables unbiased gradient approximation for differentiable point cloud rendering based on surface splatting. Our framework models the contribution of a point to the rendered ...

We present CIRCLE, a framework for large-scale scene completion and geometric refinement based on local implicit signed distance functions. It is based on an end-to-end sparse convolutional network, CircNet, which jointly models local geometric ...

Semantic scene completion (SSC) aims to jointly estimate the complete geometry and semantics of a scene, assuming partial sparse input. In the last years following the multiplication of large-scale 3D datasets, SSC has gained significant momentum ...

• The proposed solution can reconstruct indoor scenes using only a single frame and an RGB camera.

Display Omitted

Indoor environment reconstruction is a challenging task in Computer Vision and Computer Graphics, especially when Extended Reality (XR) technologies are considered. Current solutions that employ dedicated depth sensors require scanning ...

Corneal reflection extracted from an eye image identifies the relationship between the subject of the image and the scene in front of the subject. The reconstructed scene from corneal reflection provides detailed information about the environment ...

There is an increasing trend of Virtual-Reality (VR) applications found in education, entertainment, and industry. Many of them utilize real world tools, environments, and interactions as bases for creation. However, creating such applications is tedious,...

Scene reconstruction and visual localization in dynamic environments such as street scenes are a challenge due to the lack of distinctive, stable keypoints. While learned convolutional features have proven to be robust to changes in viewing ...

Shape retrieval and alignment are a promising avenue towards turning 3D scans into lightweight CAD representations that can be used for content creation such as mobile or AR/VR gaming scenarios. Unfortunately, CAD model retrieval is limited by the ...

We present a novel approach to infer volumetric reconstructions from a single viewport, based only on an RGB image and a reconstructed normal image. To overcome the problem of reconstructing regions in 3D that are occluded in the 2D image, we ...${\mathrm{}}^{\mathrm{}}$

We present a motion planner for the autonomous navigation of UAVs that manages motion and sensing uncertainty at planning time. By doing so, optimal paths in terms of probability of collision, traversal time and uncertainty are obtained. Moreover,...

• Motion planning strategy adapted to UAVs that focuses on the safety of the flight.
• Novel multi-resolution 3D heuristic which efficiently copes with the obstacles.
• Reliable estimation of the probability of collision considering the ...

Accurate and detailed information of traffic accident scene is important for accident investigation, and the current investigation methods (tape measuring and total station survey) always need highway closure, and their working process is time-...

We present an outdoor photometric stereo method using images captured in a single day. We simulate a sky hemisphere for each image according to its GPS and timestamp and parameterize the obtained sky hemisphere into quadratic skylight and Gaussian ...

The stixel-world is a compact and detailed environment representation specially designed for street scenes and automotive vision applications. A recent work proposes a monocamera based stixel estimation method based on the structure from motion ...

We propose a new multiplanar superstructure for unified real-time processing of RGB-D data. Modern RGB-D sensors are widely used for indoor 3D capture, with applications ranging from modeling to robotics, through augmented reality. Nevertheless, ...

In this paper, we focus on constructing new flexible and powerful parametric framework for visual data modeling and reconstruction. In particular, we propose a Bayesian density estimation method based upon mixtures of scaled Dirichlet ...