Related papers: 3D Gaussian Adaptive Reconstruction for Fourier Li…
We present FlashSLAM, a novel SLAM approach that leverages 3D Gaussian Splatting for efficient and robust 3D scene reconstruction. Existing 3DGS-based SLAM methods often fall short in sparse view settings and during large camera movements…
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…
3D Gaussian splatting (3DGS) is an innovative rendering technique that surpasses the neural radiance field (NeRF) in both rendering speed and visual quality by leveraging an explicit 3D scene representation. Existing 3DGS approaches require…
Fourier reconstruction algorithms significantly outperform conventional back-projection algorithms in terms of computation time. In photoacoustic imaging, these methods require interpolation in the Fourier space domain, which creates…
We present a novel three-dimensional (3D) imaging approach that combines two-dimensional spatial Fourier-domain imaging techniques with traditional radar pulse compression to recover both cross-range and down-range scene information. The…
Fast Fourier Transform based phase screen simulations give accurate results only when the screen size ($G$) is much larger than the outer scale parameter ($L_0$). Otherwise, they fall short in correctly predicting both the low and high…
We present a novel approach for enhancing the resolution and geometric fidelity of 3D Gaussian Splatting (3DGS) beyond native training resolution. Current 3DGS methods are fundamentally limited by their input resolution, producing…
Novel view synthesis from raw images provides superior high dynamic range (HDR) information compared to reconstructions from low dynamic range RGB images. However, the inherent noise in unprocessed raw images compromises the accuracy of 3D…
Neural Radiance Fields (NeRF) have been adapted for indoor 3D Object Detection (3DOD), offering a promising approach to indoor 3DOD via view-synthesis representation. But its implicit nature limits representational capacity. Recently, 3D…
Intraoperative navigation relies heavily on precise 3D reconstruction to ensure accuracy and safety during surgical procedures. However, endoscopic scenarios present unique challenges, including sparse features and inconsistent lighting,…
We propose RelitLRM, a Large Reconstruction Model (LRM) for generating high-quality Gaussian splatting representations of 3D objects under novel illuminations from sparse (4-8) posed images captured under unknown static lighting. Unlike…
Multi-view mesh reconstruction remains a core challenge in computer graphics and vision, especially for recovering high-frequency geometry from sparse observations. Recent methods such as 3D Gaussian Splatting (3DGS) and Neural Radiance…
Accurate calibration of internal parameters is a crucial yet challenging prerequisite for 3D reconstruction using light field cameras. In this paper, we propose a linear fractional transformation(LFT) parameter $\alpha$ to decoupled the…
Reconstructing high-quality 3D scenes from low-resolution multi-view images remains challenging for 3D Gaussian Splatting (3DGS), because insufficient high-frequency observations often lead to blurred textures, weak boundaries, and…
Feature extraction, matching, structure from motion (SfM), and novel view synthesis (NVS) have traditionally been treated as separate problems with independent optimization objectives. We present GloSplat, a framework that performs…
Image deblurring aims to reconstruct a latent sharp image from its corresponding blurred one. Although existing methods have achieved good performance, most of them operate exclusively in either the spatial domain or the frequency domain,…
While 3D Gaussian splatting (3DGS) offers explicit and efficient scene representations for cone-beam computed tomography reconstruction, conventional photometric optimization inherently suffers from spectral bias under ultra sparse-view…
Medical Image-to-image translation is a key task in computer vision and generative artificial intelligence, and it is highly applicable to medical image analysis. GAN-based methods are the mainstream image translation methods, but they…
Three-dimensional reconstruction in scenes with extreme depth variations remains challenging due to inconsistent supervisory signals between near-field and far-field regions. Existing methods fail to simultaneously address inaccurate depth…
A densely-sampled light field (LF) is highly desirable in various applications, such as 3-D reconstruction, post-capture refocusing and virtual reality. However, it is costly to acquire such data. Although many computational methods have…