相关论文: RL-AD-Net: Reinforcement Learning Guided Adaptive …

Reinforcement Learning (RL) has emerged as a dominant paradigm for end-to-end autonomous driving (AD). However, RL suffers from sample inefficiency and a lack of semantic interpretability in complex scenarios. Foundation Models,…

Leveraging the priors of 2D diffusion models for 3D editing has emerged as a promising paradigm. However, maintaining multi-view consistency in edited results remains challenging, and the extreme scarcity of 3D-consistent editing paired…

We present an image-conditioned point cloud completion approach that treats images as the primary geometric source rather than a secondary guide. To this end, we introduce an Image-to-Point (I2P) module that can reconstruct complete point…

With the growing demand for real-time video enhancement in live applications, existing methods often struggle to balance speed and effective exposure control, particularly under uneven lighting. We introduce RRNet (Rendering Relighting…

Despite recent advances in improving the sample-efficiency of reinforcement learning (RL) algorithms, designing an RL algorithm that can be practically deployed in real-world environments remains a challenge. In this paper, we present…

Reliable robotic grasping in unstructured environments is a crucial but challenging task. The main problem is to generate the optimal grasp of novel objects from partial noisy observations. This paper presents an end-to-end grasp detection…

This paper investigates the problem of recovering hyperspectral (HS) images from single RGB images. To tackle such a severely ill-posed problem, we propose a physically-interpretable, compact, efficient, and end-to-end learning-based…

This paper introduces Attentive Implicit Representation Networks (AIR-Nets), a simple, but highly effective architecture for 3D reconstruction from point clouds. Since representing 3D shapes in a local and modular fashion increases…

The success of deep learning methods led to significant breakthroughs in 3-D point cloud processing tasks with applications in remote sensing. Existing methods utilize convolutions that have some limitations, as they assume a uniform input…

Pre-training strategies play a critical role in advancing the performance of transformer-based models for 3D point cloud tasks. In this paper, we introduce Point-RTD (Replaced Token Denoising), a novel pretraining strategy designed to…

Autonomous vehicles rely heavily on sensors such as camera and LiDAR, which provide real-time information about their surroundings for the tasks of perception, planning and control. Typically a LiDAR can only provide sparse point cloud…

Interpretation of Airborne Laser Scanning (ALS) point clouds is a critical procedure for producing various geo-information products like 3D city models, digital terrain models and land use maps. In this paper, we present a local and global…

Point normal, as an intrinsic geometric property of 3D objects, not only serves conventional geometric tasks such as surface consolidation and reconstruction, but also facilitates cutting-edge learning-based techniques for shape analysis…

In High-definition (HD) maps, lane elements constitute the majority of components and demand stringent localization requirements to ensure safe vehicle navigation. Vision lane detection with LiDAR position assignment is a prevalent method…

We present an end-to-end Reinforcement Learning(RL) framework for robotic manipulation tasks, using a robust and efficient keypoints representation. The proposed method learns keypoints from camera images as the state representation,…

Semantic shape completion is a challenging problem in 3D computer vision where the task is to generate a complete 3D shape using a partial 3D shape as input. We propose a learning-based approach to complete incomplete 3D shapes through…

Recently, neural network compression schemes like channel pruning have been widely used to reduce the model size and computational complexity of deep neural network (DNN) for applications in power-constrained scenarios such as embedded…

Continuous diffusion and flow models are attractive for non-autoregressive text generation because they can update all positions in parallel. A major difficulty is the interface between continuous latent states and discrete tokens. This…

In this paper, we propose a Point Fractal Network (PF-Net), a novel learning-based approach for precise and high-fidelity point cloud completion. Unlike existing point cloud completion networks, which generate the overall shape of the point…

Perceiving the environment via cameras is crucial for Reinforcement Learning (RL) in robotics. While images are a convenient form of representation, they often complicate extracting important geometric details, especially with varying…