Related papers: DA$^{2}$: Depth Anything in Any Direction
We present Dur360BEV, a novel spherical camera autonomous driving dataset equipped with a high-resolution 128-channel 3D LiDAR and a RTK-refined GNSS/INS system, along with a benchmark architecture designed to generate Bird-Eye-View (BEV)…
Accurate depth estimation is at the core of many applications in computer graphics, vision, and robotics. Current state-of-the-art monocular depth estimators, trained on extensive datasets, generalize well but lack 3D consistency needed for…
Omnidirectional depth estimation enables efficient 3D perception over a full 360-degree range. However, in real-world applications such as autonomous driving and robotics, achieving real-time performance and robust cross-scene…
Accurate and efficient characterization of nanoparticle morphology in Scanning Electron Microscopy (SEM) images is critical for ensuring product quality in nanomaterial synthesis and accelerating development. However, conventional deep…
Enhancing visual odometry by exploiting sparse depth measurements from LiDAR is a promising solution for improving tracking accuracy of an odometry. Most existing works utilize a monocular pinhole camera, yet could suffer from poor…
Though there exists a reasonable forward model for blur based on optical physics, recovering depth from a collection of defocused images remains a computationally challenging optimization problem. In this paper, we show that with…
This paper presents GoodSAM++, a novel framework utilizing the powerful zero-shot instance segmentation capability of SAM (i.e., teacher) to learn a compact panoramic semantic segmentation model, i.e., student, without requiring any labeled…
Omnidirectional images, aka 360 images, can deliver immersive and interactive visual experiences. As their popularity has increased dramatically in recent years, evaluating the quality of 360 images has become a problem of interest since it…
Timely and accurate floodwater depth estimation is critical for road accessibility and emergency response. While recent computer vision methods have enabled flood detection, they suffer from both accuracy limitations and poor generalization…
Path smoothness is often overlooked in path imitation learning from expert demonstrations. In this paper, we introduce a novel learning method, termed deep angular A* (DAA*), by incorporating the proposed path angular freedom (PAF) into A*…
We introduce Stereo Anywhere, a novel stereo-matching framework that combines geometric constraints with robust priors from monocular depth Vision Foundation Models (VFMs). By elegantly coupling these complementary worlds through a…
360{\deg} depth estimation is a challenging research problem due to the difficulty of finding a representation that both preserves global continuity and avoids distortion in spherical images. Existing methods attempt to leverage…
Autonomous vehicles clearly benefit from the expanded Field of View (FoV) of 360-degree sensors, but modern semantic segmentation approaches rely heavily on annotated training data which is rarely available for panoramic images. We look at…
3D reconstruction of depth and motion from monocular video in dynamic environments is a highly ill-posed problem due to scale ambiguities when projecting to the 2D image domain. In this work, we investigate the performance of the current…
Foundation models for image segmentation have shown strong generalization in natural images, yet their applicability to 3D medical imaging remains limited. In this work, we study the zero-shot use of Segment Anything Model 2 (SAM2) for…
In this paper, we address panoramic semantic segmentation which is under-explored due to two critical challenges: (1) image distortions and object deformations on panoramas; (2) lack of semantic annotations in the 360{\deg} imagery. To…
Robust three-dimensional scene understanding is now an ever-growing area of research highly relevant in many real-world applications such as autonomous driving and robotic navigation. In this paper, we propose a multi-task learning-based…
Panoramic cameras, capable of capturing a 360-degree field of view, are crucial in robotic vision, particularly in environments with sparse features. However, non-upright panoramas due to unstable robot postures hinder downstream tasks.…
Visual place recognition has gained significant attention in recent years as a crucial technology in autonomous driving and robotics. Currently, the two main approaches are the perspective view retrieval (P2P) paradigm and the…
Top-down Bird's Eye View (BEV) maps are a popular representation for ground robot navigation due to their richness and flexibility for downstream tasks. While recent methods have shown promise for predicting BEV maps from First-Person View…