Related papers: 3D Multi-frame Fusion for Video Stabilization
Scene view synthesis, which generates novel views from limited perspectives, is increasingly vital for applications like virtual reality, augmented reality, and robotics. Unlike object-based tasks, such as generating 360{\deg} views of a…
Feedforward 3D Gaussian Splatting (3DGS) overcomes the limitations of optimization-based 3DGS by enabling fast and high-quality reconstruction without the need for per-scene optimization. However, existing feedforward approaches typically…
Camera-based 3D semantic scene completion (SSC) offers a cost-effective solution for assessing the geometric occupancy and semantic labels of each voxel in the surrounding 3D scene with image inputs, providing a voxel-level scene perception…
The research on neural radiance fields for new view synthesis has experienced explosive growth with the development of new models and extensions. The NERF algorithm, suitable for underwater scenes or scattering media, is also evolving.…
Multi-frame depth estimation generally achieves high accuracy relying on the multi-view geometric consistency. When applied in dynamic scenes, e.g., autonomous driving, this consistency is usually violated in the dynamic areas, leading to…
Image-based geometric modeling and novel view synthesis based on sparse, large-baseline samplings are challenging but important tasks for emerging multimedia applications such as virtual reality and immersive telepresence. Existing methods…
4D millimeter-wave (mmWave) radar has been widely adopted in autonomous driving and robot perception due to its low cost and all-weather robustness. However, point-cloud-based radar representations suffer from information loss due to…
This paper introduces a novel method to super-resolve multi-spectral images captured by modern real-time single-shot mosaic image sensors, also known as multi-spectral cameras. Our contribution is two-fold. Firstly, we super-resolve…
3D Gaussian Splatting (3DGS) enables high-quality novel view synthesis, motivating interest in generating higher-resolution renders than those available during training. A natural strategy is to apply super-resolution (SR) to low-resolution…
Audio data, often synchronized with video frames, plays a crucial role in guiding the audience's visual attention. Incorporating audio information into video saliency prediction tasks can enhance the prediction of human visual behavior.…
In multi-view medical diagnosis, deep learning-based models often fuse information from different imaging perspectives to improve diagnostic performance. However, existing approaches are prone to overfitting and rely heavily on…
We present a method that achieves state-of-the-art results for synthesizing novel views of complex scenes by optimizing an underlying continuous volumetric scene function using a sparse set of input views. Our algorithm represents a scene…
With the popularity of monocular videos generated by video sharing and live broadcasting applications, reconstructing and editing dynamic scenes in stationary monocular cameras has become a special but anticipated technology. In contrast to…
Low-resolution (LR) multi-view capture limits the fidelity of 3D Gaussian Splatting (3DGS). 3DGS super-resolution (SR) is therefore important, yet challenging because it must recover missing high-frequency details while enforcing cross-view…
We propose an online object-level SLAM system which builds a persistent and accurate 3D graph map of arbitrary reconstructed objects. As an RGB-D camera browses a cluttered indoor scene, Mask-RCNN instance segmentations are used to…
Remote Sensing Image-Text Retrieval (RSITR) is pivotal for knowledge services and data mining in the remote sensing (RS) domain. Considering the multi-scale representations in image content and text vocabulary can enable the models to learn…
Robots and other smart devices need efficient object-based scene representations from their on-board vision systems to reason about contact, physics and occlusion. Recognized precise object models will play an important role alongside…
3D Gaussian Splatting (3DGS) has revolutionized neural rendering with its efficiency and quality, but like many novel view synthesis methods, it heavily depends on accurate camera poses from Structure-from-Motion (SfM) systems. Although…
Reliable perception is essential for autonomous driving systems to operate safely under diverse real-world traffic conditions. However, camera- and LiDAR-based perception systems suffer from performance degradation under adverse weather and…
Conventional geometry-based SLAM systems lack dense 3D reconstruction capabilities since their data association usually relies on feature correspondences. Additionally, learning-based SLAM systems often fall short in terms of real-time…