Related papers: Shape2.5D: A Dataset of Texture-less Surfaces for …
We present a novel method for reconstructing clothed humans from a sparse set of, e.g., 1 to 6 RGB images. Despite impressive results from recent works employing deep implicit representation, we revisit the volumetric approach and…
3D scanning is a complex multistage process that generates a point cloud of an object typically containing damaged parts due to occlusions, reflections, shadows, scanner motion, specific properties of the object surface, imperfect…
3D object reconstruction from a single image is a highly under-determined problem, requiring strong prior knowledge of plausible 3D shapes. This introduces challenges for learning-based approaches, as 3D object annotations are scarce in…
Reflective and textureless surfaces remain a challenge in multi-view 3D reconstruction. Both camera pose calibration and shape reconstruction often fail due to insufficient or unreliable cross-view visual features. To address these issues,…
Due to the optical properties, transparent objects often lead depth cameras to generate incomplete or invalid depth data, which in turn reduces the accuracy and reliability of robotic grasping. Existing approaches typically input the RGB-D…
Recently, 3D anomaly detection, a crucial problem involving fine-grained geometry discrimination, is getting more attention. However, the lack of abundant real 3D anomaly data limits the scalability of current models. To enable scalable…
Visual object tracking has focused predominantly on opaque objects, while transparent object tracking received very little attention. Motivated by the uniqueness of transparent objects in that their appearance is directly affected by the…
The development of large-scale 3D scene reconstruction and novel view synthesis methods mostly rely on datasets comprising perspective images with narrow fields of view (FoV). While effective for small-scale scenes, these datasets require…
Depth-image-based rendering is a key view synthesis algorithm in 3D video systems, which enables the synthesis of virtual views from texture images and depth maps. An efficient view synthesis distortion estimation model is critical for…
Existing point cloud modeling datasets primarily express the modeling precision by pose or trajectory precision rather than the point cloud modeling effect itself. Under this demand, we first independently construct a set of LiDAR system…
This work tackles 3D scene reconstruction for a video fly-over perspective problem in the maritime domain, with a specific emphasis on geometrically and visually sound reconstructions. This will allow for downstream tasks such as…
Recent advances in radiance fields and novel view synthesis enable creation of realistic digital twins from photographs. However, current methods struggle with flat, texture-less surfaces, creating uneven and semi-transparent…
In this paper, we propose several mathematical models for 3D surface reconstruction and volume estimation from a set of scattered cloud data. Three meshless methods including the interpolation-based method by RBF, PDE-based approach by…
We propose PSSNet, a network architecture for generating diverse plausible 3D reconstructions from a single 2.5D depth image. Existing methods tend to produce only small variations on a single shape, even when multiple shapes are consistent…
We present a novel neural surface reconstruction method called NeuralRoom for reconstructing room-sized indoor scenes directly from a set of 2D images. Recently, implicit neural representations have become a promising way to reconstruct…
Neural surface reconstruction has been dominated by implicit representations with marching cubes for explicit surface extraction. However, those methods typically require high-quality normals for accurate reconstruction. We propose…
Recently, 3D face reconstruction from a single image has achieved great success with the help of deep learning and shape prior knowledge, but they often fail to produce accurate geometry details. On the other hand, photometric stereo…
This paper addresses the growing demands for safety and comfort in intelligent robot systems, particularly autonomous vehicles, where road conditions play a pivotal role in overall driving performance. For example, reconstructing road…
Transparent object depth perception poses a challenge in everyday life and logistics, primarily due to the inability of standard 3D sensors to accurately capture depth on transparent or reflective surfaces. This limitation significantly…
Lensless imaging has emerged as a potential solution towards realizing ultra-miniature cameras by eschewing the bulky lens in a traditional camera. Without a focusing lens, the lensless cameras rely on computational algorithms to recover…