Related papers: VGF-Net: Visual-Geometric Fusion Learning for Simu…

Fusion of 2D images and 3D point clouds is important because information from dense images can enhance sparse point clouds. However, fusion is challenging because 2D and 3D data live in different spaces. In this work, we propose MVPNet…

Image restoration has seen substantial progress in recent years. However, existing methods often neglect depth information, which hurts similarity matching, results in attention distractions in shallow depth-of-field (DoF) scenarios, and…

Information inside visual and LiDAR data is well complementary derived from the fine-grained texture of images and massive geometric information in point clouds. However, it remains challenging to explore effective visual-LiDAR fusion,…

Learning fine-grained details is a key issue in image aesthetic assessment. Most of the previous methods extract the fine-grained details via random cropping strategy, which may undermine the integrity of semantic information. Extensive…

Robust and realistic rendering for large-scale road scenes is essential in autonomous driving simulation. Recently, 3D Gaussian Splatting (3D-GS) has made groundbreaking progress in neural rendering, but the general fidelity of large-scale…

This paper presents VGGT-360, a novel training-free framework for zero-shot, geometry-consistent panoramic depth estimation. Unlike prior view-independent training-free approaches, VGGT-360 reformulates the task as panoramic reprojection…

Humans naturally perceive a 3D scene in front of them through accumulation of information obtained from multiple interconnected projections of the scene and by interpreting their correspondence. This phenomenon has inspired artificial…

Although large-scale visual foundation models (VFMs) achieve remarkable performance in semantic understanding, they still underperform in instance-aware dense prediction tasks. They exhibit different biases in representation: for instance,…

Detecting Unmanned Aerial Vehicles (UAVs) in low-altitude environments is essential for perception and defense systems but remains highly challenging due to complex backgrounds, camouflage, and multimodal interference. In real-world…

Camera and LiDAR sensor modalities provide complementary appearance and geometric information useful for detecting 3D objects for autonomous vehicle applications. However, current end-to-end fusion methods are challenging to train and…

Existing Visual Question Answering (VQA) models have explored various visual relationships between objects in the image to answer complex questions, which inevitably introduces irrelevant information brought by inaccurate object detection…

Learning accurate scene reconstruction without pose priors in neural radiance fields is challenging due to inherent geometric ambiguity. Recent development either relies on correspondence priors for regularization or uses off-the-shelf flow…

Stereo-LiDAR fusion is a promising task in that we can utilize two different types of 3D perceptions for practical usage -- dense 3D information (stereo cameras) and highly-accurate sparse point clouds (LiDAR). However, due to their…

Drones are increasingly used in fields like industry, medicine, research, disaster relief, defense, and security. Technical challenges, such as navigation in GPS-denied environments, hinder further adoption. Research in visual odometry is…

We present 3DVNet, a novel multi-view stereo (MVS) depth-prediction method that combines the advantages of previous depth-based and volumetric MVS approaches. Our key idea is the use of a 3D scene-modeling network that iteratively updates a…

With the expanding application scope of unmanned aerial vehicles (UAVs), the demand for stable UAV control has significantly increased. However, in complex environments, GPS signals are prone to interference, resulting in ineffective UAV…

Many recent works on 3D object detection have focused on designing neural network architectures that can consume point cloud data. While these approaches demonstrate encouraging performance, they are typically based on a single modality and…

Modern 3D computer vision leverages learning to boost geometric reasoning, mapping image data to classical structures such as cost volumes or epipolar constraints to improve matching. These architectures are specialized according to the…

Accurate motion tracking of snow particles in avalanche events requires robust localization in global navigation satellite system (GNSS)-denied outdoor environments. This paper introduces AoI-FusionNet, a tightly coupled deep learning-based…

In this work, we present FFB6D, a Full Flow Bidirectional fusion network designed for 6D pose estimation from a single RGBD image. Our key insight is that appearance information in the RGB image and geometry information from the depth image…