Related papers: SparseFormer: Attention-based Depth Completion Net…

In this paper, we propose a deep learning architecture that produces accurate dense depth for the outdoor scene from a single color image and a sparse depth. Inspired by the indoor depth completion, our network estimates surface normals as…

Referring image segmentation aims to segment an object referred to by natural language expression from an image. The primary challenge lies in the efficient propagation of fine-grained semantic information from textual features to visual…

Medical image segmentation is a critical task that plays a vital role in diagnosis, treatment planning, and disease monitoring. Accurate segmentation of anatomical structures and abnormalities from medical images can aid in the early…

We present Dense-SfM, a novel Structure from Motion (SfM) framework designed for dense and accurate 3D reconstruction from multi-view images. Sparse keypoint matching, which traditional SfM methods often rely on, limits both accuracy and…

Sparse-view reconstruction models typically require precise camera poses, yet obtaining these parameters from sparse-view images remains challenging. We introduce FreeSplatter, a scalable feed-forward framework that generates high-quality…

Semantic Segmentation is a crucial component in the perception systems of many applications, such as robotics and autonomous driving that rely on accurate environmental perception and understanding. In literature, several approaches are…

Due to the computational complexity of self-attention (SA), prevalent techniques for image deblurring often resort to either adopting localized SA or employing coarse-grained global SA methods, both of which exhibit drawbacks such as…

LiDAR-based 3D object detection plays an essential role in autonomous driving. Existing high-performing 3D object detectors usually build dense feature maps in the backbone network and prediction head. However, the computational costs…

In many applications, maintaining a consistent dense map of the environment is key to enabling robotic platforms to perform higher level decision making. Several works have addressed the challenge of creating precise dense 3D maps from…

Large pre-trained transformers have revolutionized artificial intelligence across various domains, and fine-tuning remains the dominant approach for adapting these models to downstream tasks due to the cost of training from scratch.…

We present a visual simultaneous localization and mapping (SLAM) framework of closing surface loops. It combines both sparse feature matching and dense surface alignment. Sparse feature matching is used for visual odometry and globally…

As the core building block of vision transformers, attention is a powerful tool to capture long-range dependency. However, such power comes at a cost: it incurs a huge computation burden and heavy memory footprint as pairwise token…

Autonomous field robots operating in unstructured environments require robust perception to ensure safe and reliable operations. Recent advances in monocular depth estimation have demonstrated the potential of low-cost cameras as depth…

Vision Transformers with various attention modules have demonstrated superior performance on vision tasks. While using sparsity-adaptive attention, such as in DAT, has yielded strong results in image classification, the key-value pairs…

We present Wave-Former, a novel method capable of high-accuracy 3D shape reconstruction for completely occluded, diverse, everyday objects. This capability can open new applications spanning robotics, augmented reality, and logistics. Our…

Multi-map Sparse Monocular visual Simultaneous Localization and Mapping applied to monocular endoscopic sequences has proven efficient to robustly recover tracking after the frequent losses in endoscopy due to motion blur, temporal…

Image matching, which establishes correspondences between two-view images to recover 3D structure and camera geometry, serves as a cornerstone in computer vision and underpins a wide range of applications, including visual localization, 3D…

Most approaches for semantic segmentation use only information from color cameras to parse the scenes, yet recent advancements show that using depth data allows to further improve performances. In this work, we focus on transformer-based…

Open-world 3D reconstruction models have recently garnered significant attention. However, without sufficient 3D inductive bias, existing methods typically entail expensive training costs and struggle to extract high-quality 3D meshes. In…

Computer vision and image processing applications suffer from dark and low-light images, particularly during real-time image transmission. Currently, low light and dark images are converted to bright and colored forms using autoencoders;…