Related papers: ProJo4D: Progressive Joint Optimization for Sparse…
Sparse-view 3D reconstruction is essential for applications in which dense image acquisition is impractical, such as robotics, augmented/virtual reality (AR/VR), and autonomous systems. In these settings, minimal image overlap prevents…
Neural rendering methods have gained significant attention for their ability to reconstruct 3D scenes from 2D images. The core idea is to take multiple views as input and optimize the reconstructed scene by minimizing the uncertainty in…
Due to inevitable noises introduced during scanning and quantization, 3D reconstruction via RGB-D sensors suffers from errors both in geometry and texture, leading to artifacts such as camera drifting, mesh distortion, texture ghosting, and…
Reconstructing dynamic 3D scenes from sparse multi-view videos is highly ill-posed, often leading to geometric collapse, trajectory drift, and floating artifacts. Recent attempts introduce generative priors to hallucinate missing content,…
Meta-optics promises compact, high-performance imaging and color routing. However, designing high-performance structures is a high-dimensional optimization problem: mapping a desired optical output back to a physical 3D structure requires…
Reconstructing 3D scenes from sparse viewpoints is a long-standing challenge with wide applications. Recent advances in feed-forward 3D Gaussian sparse-view reconstruction methods provide an efficient solution for real-time novel view…
We introduce Intrinsic Image Fusion, a method that reconstructs high-quality physically based materials from multi-view images. Material reconstruction is highly underconstrained and typically relies on analysis-by-synthesis, which requires…
Sparse algorithms offer great flexibility for multi-view temporal perception tasks. In this paper, we present an enhanced version of Sparse4D, in which we improve the temporal fusion module by implementing a recursive form of multi-frame…
Many crucial tasks of image processing and computer vision are formulated as inverse problems. Thus, it is of great importance to design fast and robust algorithms to solve these problems. In this paper, we focus on generalized projected…
Reconstructing an accurate 3D object model from a few image observations remains a challenging problem in computer vision. State-of-the-art approaches typically assume accurate camera poses as input, which could be difficult to obtain in…
Neural implicit representations have revolutionized dense multi-view surface reconstruction, yet their performance significantly diminishes with sparse input views. A few pioneering works have sought to tackle the challenge of sparse-view…
Gaussian Splatting has been considered as a novel way for view synthesis of dynamic scenes, which shows great potential in AIoT applications such as digital twins. However, recent dynamic Gaussian Splatting methods significantly degrade…
Implicit neural representation has demonstrated promising results in 3D reconstruction on various scenes. However, existing approaches either struggle to model fast-moving objects or are incapable of handling large-scale camera ego-motions…
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…
Four-dimensional (4D) radar--visual odometry (4DRVO) integrates complementary information from 4D radar and cameras, making it an attractive solution for achieving accurate and robust pose estimation. However, 4DRVO may exhibit significant…
We present ZeroRF, a novel per-scene optimization method addressing the challenge of sparse view 360{\deg} reconstruction in neural field representations. Current breakthroughs like Neural Radiance Fields (NeRF) have demonstrated…
Many imaging technologies rely on tomographic reconstruction, which requires solving a multidimensional inverse problem given a finite number of projections. Backprojection is a popular class of algorithm for tomographic reconstruction,…
4D time-space reconstruction of dynamic events or deforming objects using X-ray computed tomography (CT) is an important inverse problem in non-destructive evaluation. Conventional back-projection based reconstruction methods assume that…
Reconstructing real-world objects from multi-view images is essential for applications in 3D editing, AR/VR, and digital content creation. Existing methods typically prioritize either geometric accuracy (Multi-View Stereo) or photorealistic…
In the field of global optimization, many existing algorithms face challenges posed by non-convex target functions and high computational complexity or unavailability of gradient information. These limitations, exacerbated by sensitivity to…