Related papers: Voxel Densification for Serialized 3D Object Detec…
Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations. However, the former requires time-consuming sampling while the latter introduces quantization errors. In this paper,…
Video Object Segmentation (VOS) is foundational to numerous computer vision applications, including surveillance, autonomous driving, robotics and generative video editing. However, existing VOS models often struggle with precise mask…
This letter introduces a novel framework for dense Visual Simultaneous Localization and Mapping (VSLAM) based on Gaussian Splatting. Recently, SLAM based on Gaussian Splatting has shown promising results. However, in monocular scenarios,…
We propose SFMNet, a novel 3D sparse detector that combines the efficiency of sparse convolutions with the ability to model long-range dependencies. While traditional sparse convolution techniques efficiently capture local structures, they…
Vision Transformer (ViT) has achieved remarkable results in object detection for synthetic aperture radar (SAR) images, owing to its exceptional ability to extract global features. However, it struggles with the extraction of multi-scale…
Recent advances in Vision-Language Models (VLMs) have enabled unified understanding across text and images, yet equipping these models with robust image generation capabilities remains challenging. Existing approaches often rely on…
We propose an efficient radiance field rendering algorithm that incorporates a rasterization process on adaptive sparse voxels without neural networks or 3D Gaussians. There are two key contributions coupled with the proposed system. The…
The 3D point cloud perception has emerged as a fundamental role for a wide range of applications. In particular, with the rapid development of neural networks, the voxel-based networks attract great attention due to their excellent…
Detecting objects in 3D LiDAR data is a core technology for autonomous driving and other robotics applications. Although LiDAR data is acquired over time, most of the 3D object detection algorithms propose object bounding boxes…
Vision-Language Model (VLM) have gained widespread adoption in Open-Vocabulary (OV) object detection and segmentation tasks. Despite they have shown promise on OV-related tasks, their effectiveness in conventional vision tasks has thus far…
Real-world video super-resolution (VSR) presents significant challenges due to complex and unpredictable degradations. Although some recent methods utilize image diffusion models for VSR and have shown improved detail generation…
Accurate 3D object detection from point clouds has become a crucial component in autonomous driving. However, the volumetric representations and the projection methods in previous works fail to establish the relationships between the local…
Vision Language Models (VLMs) offer the exciting possibility of processing text as rendered images, bypassing the need for tokenizing the text into long token sequences. Since VLM image encoders map fixed-size images to a fixed number of…
In the domain of large foundation models, the Segment Anything Model (SAM) has gained notable recognition for its exceptional performance in image segmentation. However, tackling the video camouflage object detection (VCOD) task presents a…
Roadside vision centric 3D object detection has received increasing attention in recent years. It expands the perception range of autonomous vehicles, enhances the road safety. Previous methods focused on predicting per-pixel height rather…
Multi-view 3D object detection is a fundamental task in autonomous driving perception, where achieving a balance between detection accuracy and computational efficiency remains crucial. Sparse query-based 3D detectors efficiently aggregate…
Denoising Diffusion Probabilistic Models (DDPMs) have shown success in robust 3D object detection tasks. Existing methods often rely on the score matching from 3D boxes or pre-trained diffusion priors. However, they typically require…
We consider the problem of scaling deep generative shape models to high-resolution. Drawing motivation from the canonical view representation of objects, we introduce a novel method for the fast up-sampling of 3D objects in voxel space…
Current Point-based detectors can only learn from the provided points, with limited receptive fields and insufficient global learning capabilities for such targets. In this paper, we present a novel Point Dilation Mechanism for single-stage…
Despite the remarkable progress, weakly supervised segmentation approaches are still inferior to their fully supervised counterparts. We obverse the performance gap mainly comes from their limitation on learning to produce high-quality…