Related papers: Revisiting 360 Depth Estimation with PanoGabor: A …
Accurate endoscope pose estimation and 3D tissue surface reconstruction significantly enhances monocular minimally invasive surgical procedures by enabling accurate navigation and improved spatial awareness. However, monocular endoscope…
We propose Radar-Camera fusion transformer (RaCFormer) to boost the accuracy of 3D object detection by the following insight. The Radar-Camera fusion in outdoor 3D scene perception is capped by the image-to-BEV transformation--if the depth…
We design a multiscopic vision system that utilizes a low-cost monocular RGB camera to acquire accurate depth estimation. Unlike multi-view stereo with images captured at unconstrained camera poses, the proposed system controls the motion…
Existing fusion methods are tailored for high-quality images but struggle with degraded images captured under harsh circumstances, thus limiting the practical potential of image fusion. This work presents a \textbf{D}egradation and…
Radar-Camera depth estimation aims to predict dense and accurate metric depth by fusing input images and Radar data. Model efficiency is crucial for this task in pursuit of real-time processing on autonomous vehicles and robotic platforms.…
Image deraining have have gained a great deal of attention in order to address the challenges posed by the effects of harsh weather conditions on visual tasks. While convolutional neural networks (CNNs) are popular, their limitations in…
This paper presents a unified framework for depth-aware panoptic segmentation (DPS), which aims to reconstruct 3D scene with instance-level semantics from one single image. Prior works address this problem by simply adding a dense depth…
3D human pose estimation has wide applications in fields such as intelligent surveillance, motion capture, and virtual reality. However, in real-world scenarios, issues such as occlusion, noise interference, and missing viewpoints can…
Wide field-of-view (FOV) cameras, which capture a larger scene area than narrow FOV cameras, are used in many applications including 3D reconstruction, autonomous driving, and video surveillance. However, wide-angle images contain…
Depth estimation is a critical technology in autonomous driving, and multi-camera systems are often used to achieve a 360$^\circ$ perception. These 360$^\circ$ camera sets often have limited or low-quality overlap regions, making multi-view…
In many real-world scenarios, recorded videos suffer from accidental focus blur, and while video deblurring methods exist, most specifically target motion blur or spatial-invariant blur. This paper introduces a framework optimized for the…
Semantic Segmentation plays a pivotal role in many applications related to medical image and video analysis. However, designing a neural network architecture for medical image and surgical video segmentation is challenging due to the…
Prior panorama stitching approaches heavily rely on pairwise feature correspondences and are unable to leverage geometric consistency across multiple views. This leads to severe distortion and misalignment, especially in challenging scenes…
This paper presents a new system to obtain dense object reconstructions along with 6-DoF poses from a single image. Geared towards high fidelity reconstruction, several recent approaches leverage implicit surface representations and deep…
Reconstructing complete and interactive 3D scenes remains a fundamental challenge in computer vision and robotics, particularly due to persistent object occlusions and limited sensor coverage. Multiview observations from a single scene scan…
Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. While prevalent multi-modal methods simply decorate raw lidar point clouds with camera features and feed them directly to…
Single-image 3D reconstruction with large reconstruction models (LRMs) has advanced rapidly, yet reconstructions often exhibit geometric inconsistencies and misaligned details that limit fidelity. We introduce GeoFusionLRM, a geometry-aware…
With the emergence of VR and AR, 360{\deg} data attracts increasing attention from the computer vision and multimedia communities. Typically, 360{\deg} data is projected into 2D ERP (equirectangular projection) images for feature…
Neural rendering has demonstrated remarkable success in high-quality 3D neural reconstruction and novel view synthesis with dense input views and accurate poses. However, applying it to extremely sparse, unposed views in unbounded 360{\deg}…
Recent Blind Image Super-Resolution (BSR) methods have shown proficiency in general images. However, we find that the efficacy of recent methods obviously diminishes when employed on image data with blur, while image data with intentional…