Related papers: RL-AD-Net: Reinforcement Learning Guided Adaptive …

Real-scanned point clouds are often incomplete due to viewpoint, occlusion, and noise. Existing point cloud completion methods tend to generate global shape skeletons and hence lack fine local details. Furthermore, they mostly learn a…

Large language models (LLMs) based on the generative pre-training transformer (GPT) have demonstrated remarkable effectiveness across a diverse range of downstream tasks. Inspired by the advancements of the GPT, we present PointGPT, a novel…

We present RoarNet, a new approach for 3D object detection from a 2D image and 3D Lidar point clouds. Based on two-stage object detection framework with PointNet as our backbone network, we suggest several novel ideas to improve 3D object…

Recently MLP-based methods have shown strong performance in point cloud analysis. Simple MLP architectures are able to learn geometric features in local point groups yet fail to model long-range dependencies directly. In this paper, we…

Change Detection is a crucial but extremely challenging task of remote sensing image analysis, and much progress has been made with the rapid development of deep learning. However, most existing deep learning-based change detection methods…

Recently, feature relation learning has drawn widespread attention in cross-spectral image patch matching. However, existing related research focuses on extracting diverse relations between image patch features and ignores sufficient…

Reinforcement learning (RL) has improved guided image generation with diffusion models by directly optimizing rewards that capture image quality, aesthetics, and instruction following capabilities. However, the resulting generative policies…

Segmentation of three-dimensional (3D) point clouds is an important task for autonomous systems. However, success of segmentation algorithms depends greatly on the quality of the underlying point clouds (resolution, completeness etc.). In…

Existing learning-based methods effectively reconstruct HDR images from multi-exposure LDR inputs with extended dynamic range and improved detail, but they rely more on empirical design rather than theoretical foundation, which can impact…

3D geometry is a very informative cue when interacting with and navigating an environment. This writing proposes a new approach to 3D reconstruction and scene understanding, which implicitly learns 3D geometry from depth maps pairing a deep…

Digital twins require continuous maintenance to meet the increasing demand for high-precision geospatial data. However, traditional coarse CityGML building models, typically derived from Airborne Laser Scanning (ALS), often exhibit…

Learning from visual observations is a fundamental yet challenging problem in Reinforcement Learning (RL). Although algorithmic advances combined with convolutional neural networks have proved to be a recipe for success, current methods are…

Image retrieval-based cross-view geo-localization (IRCVGL) aims to match images captured from significantly different viewpoints, such as satellite and street-level images. Existing methods predominantly rely on learning robust global…

Recent semantic segmentation research has increasingly moved toward stronger context modeling, dense attention, and transformer-based architectures. Although these models achieve impressive performance, classical CNN-based segmentation…

There have been recent efforts to learn more meaningful representations via fixed length codewords from mesh data, since a mesh serves as a complete model of underlying 3D shape compared to a point cloud. However, the mesh connectivity…

In this paper, we propose an end-to-end deep learning network named 3dDepthNet, which produces an accurate dense depth image from a single pair of sparse LiDAR depth and color image for robotics and autonomous driving tasks. Based on the…

Three-dimensional object recognition has recently achieved great progress thanks to the development of effective point cloud-based learning frameworks, such as PointNet and its extensions. However, existing methods rely heavily on fully…

Federated fine-tuning enables privacy-preserving LLM adaptation but faces a critical bottleneck: the disparity between LLMs' high memory demands and edge devices' limited capacity. To break the memory barrier, we propose Chain Federated…

Inspired by the success of reinforcement learning (RL) in refining large language models (LLMs), we propose AR-GRPO, an approach to integrate online RL training into autoregressive (AR) image generation models. We adapt the Group Relative…

Unsupervised non-rigid point cloud shape correspondence underpins a multitude of 3D vision tasks, yet itself is non-trivial given the exponential complexity stemming from inter-point degree-of-freedom, i.e., pose transformations. Based on…