Related papers: Structural Multiplane Image: Bridging Neural View …
We present a new method for lightweight novel-view synthesis that generalizes to an arbitrary forward-facing scene. Recent approaches are computationally expensive, require per-scene optimization, or produce a memory-expensive…
This study presents a hybrid deep learning framework, the Vision Transformer with Residual Feature Network (VRF-Net), for recovering high-resolution system matrices in Magnetic Particle Imaging (MPI). MPI resolution often suffers from…
Single-image piece-wise planar 3D reconstruction aims to simultaneously segment plane instances and recover 3D plane parameters from an image. Most recent approaches leverage convolutional neural networks (CNNs) and achieve promising…
The growing prevalence of intelligent manufacturing and autonomous vehicles has intensified the demand for three-dimensional (3D) reconstruction under complex reflection and transmission conditions. Traditional structured light techniques…
Surface reconstruction has traditionally relied on the Multi-View Stereo (MVS)-based pipeline, which often suffers from noisy and incomplete geometry. This is due to that although MVS has been proven to be an effective way to recover the…
Volume-based indoor scene reconstruction methods offer superior generalization capability and real-time deployment potential. However, existing methods rely on multi-view pixel back-projection ray intersections as weak geometric constraints…
Neural Radiance Field (NeRF) has shown impressive results in novel view synthesis, particularly in Virtual Reality (VR) and Augmented Reality (AR), thanks to its ability to represent scenes continuously. However, when just a few input view…
This paper tackles the problem of novel view synthesis from a single image. In particular, we target real-world scenes with rich geometric structure, a challenging task due to the large appearance variations of such scenes and the lack of…
Partial occlusion effects are a phenomenon that blurry objects near a camera are semi-transparent, resulting in partial appearance of occluded background. However, it is challenging for existing bokeh rendering methods to simulate realistic…
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…
3D object reconstruction from single-view image is a fundamental task in computer vision with wide-ranging applications. Recent advancements in Large Reconstruction Models (LRMs) have shown great promise in leveraging multi-view images…
Advancements in adapting deep convolution architectures for Spiking Neural Networks (SNNs) have significantly enhanced image classification performance and reduced computational burdens. However, the inability of Multiplication-Free…
Panoramic observation using fisheye cameras is significant in virtual reality (VR) and robot perception. However, panoramic images synthesized by traditional methods lack depth information and can only provide three degrees-of-freedom…
Purpose: The goal of this work is to extend the capabilities of RAKI, a k-space interpolating neural network, to reconstruct high-quality images from in-plane accelerated simultaneous multislice imaging acquisitions. This method is referred…
We present a method to map 2D image observations of a scene to a persistent 3D scene representation, enabling novel view synthesis and disentangled representation of the movable and immovable components of the scene. Motivated by the…
This paper presents a neural incremental Structure-from-Motion (SfM) approach, Level-S$^2$fM, which estimates the camera poses and scene geometry from a set of uncalibrated images by learning coordinate MLPs for the implicit surfaces and…
Synthetic aperture imaging has enabled breakthrough observations from radar to astronomy. However, optical implementation remains challenging due to stringent wavefield synchronization requirements among multiple receivers. Here we present…
The semantic representation of deep features is essential for image context understanding, and effective fusion of features with different semantic representations can significantly improve the model's performance on salient object…
The paper studies planar surface reconstruction of indoor scenes from two views with unknown camera poses. While prior approaches have successfully created object-centric reconstructions of many scenes, they fail to exploit other…
State Space Models (SSMs), especially recent Mamba architecture, have achieved remarkable success in sequence modeling tasks. However, extending SSMs to computer vision remains challenging due to the non-sequential structure of visual data…