Related papers: INGeo: Accelerating Instant Neural Scene Reconstru…

Recently, learning multi-view neural surface reconstruction with the supervision of point clouds or depth maps has been a promising way. However, due to the underutilization of prior information, current methods still struggle with the…

Recently, it has shown that priors are vital for neural implicit functions to reconstruct high-quality surfaces from multi-view RGB images. However, current priors require large-scale pre-training, and merely provide geometric clues without…

In 3D object mapping, category-level priors enable efficient object reconstruction and canonical pose estimation, requiring only a single prior per semantic category (e.g., chair, book, laptop, etc.). DeepSDF has been used predominantly as…

Recent advances in neural implicit surfaces for multi-view 3D reconstruction primarily focus on improving large-scale surface reconstruction accuracy, but often produce over-smoothed geometries that lack fine surface details. To address…

Volumetric neural rendering methods like NeRF generate high-quality view synthesis results but are optimized per-scene leading to prohibitive reconstruction time. On the other hand, deep multi-view stereo methods can quickly reconstruct…

Neural Radiance Field (NeRF), as an implicit 3D scene representation, lacks inherent ability to accommodate changes made to the initial static scene. If objects are reconfigured, it is difficult to update the NeRF to reflect the new state…

3D reconstruction of large scenes is a challenging problem due to the high-complexity nature of the solution space, in particular for generative neural networks. In contrast to traditional generative learned models which encode the full…

Recently, neural implicit functions have demonstrated remarkable results in the field of multi-view reconstruction. However, most existing methods are tailored for dense views and exhibit unsatisfactory performance when dealing with sparse…

Modeling 3D scenes by volumetric feature grids is one of the promising directions of neural approximations to improve Neural Radiance Fields (NeRF). Instant-NGP (INGP) introduced multi-resolution hash encoding from a lookup table of…

Parallel imaging is a widely-used technique to accelerate magnetic resonance imaging (MRI). However, current methods still perform poorly in reconstructing artifact-free MRI images from highly undersampled k-space data. Recently, implicit…

Scene recovery is a fundamental imaging task for several practical applications, e.g., video surveillance and autonomous vehicles, etc. To improve visual quality under different weather/imaging conditions, we propose a real-time light…

Image segmentation plays an important role in computer vision, object detection, traffic control, and video surveillance. Typically, it is a critical step in the 3D reconstruction of a specific organ in medical image processing which…

Recent advances in neural rendering have shown that, albeit slow, implicit compact models can learn a scene's geometries and view-dependent appearances from multiple views. To maintain such a small memory footprint but achieve faster…

Surface reconstruction with preservation of geometric features is a challenging computer vision task. Despite significant progress in implicit shape reconstruction, state-of-the-art mesh extraction methods often produce aliased,…

Implicit Neural Representations (INRs) are widely used for modeling continuous 2D images, enabling high-fidelity reconstruction, super-resolution, and compression. Architectures such as SIREN, WIRE, and FINER demonstrate their ability to…

Reconstructing objects from posed images is a crucial and complex task in computer graphics and computer vision. While NeRF-based neural reconstruction methods have exhibited impressive reconstruction ability, they tend to be…

We present a technique for dense 3D reconstruction of objects using an imaging sonar, also known as forward-looking sonar (FLS). Compared to previous methods that model the scene geometry as point clouds or volumetric grids, we represent…

Neural rendering can be used to reconstruct implicit representations of shapes without 3D supervision. However, current neural surface reconstruction methods have difficulty learning high-frequency geometry details, so the reconstructed…

Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their…

Recent techniques on implicit geometry representation learning and neural rendering have shown promising results for 3D clothed human reconstruction from sparse video inputs. However, it is still challenging to reconstruct detailed surface…