The popularity of LiDAR devices and sensor technology has gradually empowered users from autonomous driving to forest monitoring, and research on 3D LiDAR has made remarkable progress over the years. Unlike 2D images,...
详细信息
ISBN:
(纸本)9798350374490;9798350374506
The popularity of LiDAR devices and sensor technology has gradually empowered users from autonomous driving to forest monitoring, and research on 3D LiDAR has made remarkable progress over the years. Unlike 2D images, whose focused area is visible and rich in texture information, understanding the point distribution can help companies and researchers find better ways to develop point-based 3D applications. In this work, we contribute an unreal-based LiDAR simulation tool and a 3D simulation dataset named LiDAR-Forest, which can be used by various studies to evaluate forest reconstruction, tree DBH estimation, and point cloud compression for easy visualization. The simulation is customizable in tree species, LiDAR types and scene generation, with low cost and high efficiency.
In real-time rendering, the global illumination technique can effectively increase the realism of scene rendering, and the DDGI([5]) algorithm can well calculate the diffuse reflection effect in the scene in real-time...
详细信息
ISBN:
(纸本)9798400718267
In real-time rendering, the global illumination technique can effectively increase the realism of scene rendering, and the DDGI([5]) algorithm can well calculate the diffuse reflection effect in the scene in real-time, but the specular reflection effect needs to be combined with other algorithms for additional calculations, such as SSR[2], etc. In this paper we propose a new way of calculating specular reflections, i.e. an SSR implementation that reuses the DDGI probe Irradiance data, for the specular reflection information of some pixel locations on the screen with low metallicity and high roughness, we directly sample the irradiance data of the nearing probes as the fuzzy radiance data. In order to increase the reflection detail information, we add an additional high-resolution texture for each probe to store the blurred radiance information. Experiments show that our proposed specular light computation method can accelerate the SSR computation process while guaranteeing the rendering effect.
Mesh denoising (MD) is a critical task in geometry processing, as meshes from scanning or AIGC techniques are susceptible to noise contamination. The challenge of MD lies in the diverse nature of mesh facets in terms ...
详细信息
ISBN:
(纸本)9798350353013;9798350353006
Mesh denoising (MD) is a critical task in geometry processing, as meshes from scanning or AIGC techniques are susceptible to noise contamination. The challenge of MD lies in the diverse nature of mesh facets in terms of geometric characteristics and noise distributions. Despite recent advancements in deep learning-based MD methods, existing MD networks typically neglect the consideration of geometric characteristics and noise distributions. In this paper, we propose Hyper-MD, a hyper-network-based approach that addresses this limitation by dynamically customizing denoising parameters for each facet based on its noise intensity and geometric characteristics. Specifically, HyperMD is composed of a hyper-network and an MD network. For each noisy facet, the hyper-network takes two angles as input to customize parameters for the MD network. These two angles are specially defined to reveal the noise intensity and geometric characteristics of the current facet, respectively. The MD network receives a facet patch as input, and outputs the denoised normal using the customized parameters. Experimental results on synthetic and real-scanned meshes demonstrate that Hyper-MD outperforms state-of-the-art mesh denoising methods.
Photometric stereo leverages variations in illumination conditions to reconstruct surface normals. Display photometric stereo, which employs a conventional monitor as an illumination source, has the potential to overc...
详细信息
ISBN:
(纸本)9798350353006
Photometric stereo leverages variations in illumination conditions to reconstruct surface normals. Display photometric stereo, which employs a conventional monitor as an illumination source, has the potential to overcome limitations often encountered in bulky and difficult-to-use conventional setups. In this paper, we present differentiable display photometric stereo (DDPS), addressing an often over-looked challenge in display photometric stereo: the design of display patterns. Departing from using heuristic display patterns, DDPS learns the display patterns that yield accurate normal reconstruction for a target system in an end-to-end manner. To this end, we propose a differentiable framework that couples basis-illumination image formation with analytic photometric-stereo reconstruction. The differentiable framework facilitates the effective learning of display patterns via auto-differentiation. Also, for training supervision, we propose to use 3D printing for creating a real-world training dataset, enabling accurate reconstruction on the target real-world setup. Finally, we exploit that conventional LCD monitors emit polarized light, which allows for the optical separation of diffuse and specular reflections when combined with a polarization camera, leading to accurate normal reconstruction. Extensive evaluation of DDPS shows improved normal-reconstruction accuracy compared to heuristic patterns and demonstrates compelling properties such as robustness to pattern initialization, calibration errors, and simplifications in image formation and reconstruction.
Metaverse has been attracting more and more attention because of its potential for various use cases. In metaverse applications, the seamless integration of digital and physical worlds is vital for synchronizing infor...
详细信息
ISBN:
(纸本)9798350374490;9798350374506
Metaverse has been attracting more and more attention because of its potential for various use cases. In metaverse applications, the seamless integration of digital and physical worlds is vital for synchronizing information from one world to another. One way to achieve this is to reconstruct 3D environmental maps every time, which is not feasible due to computational complexity. A cheaper alternative is to detect what objects have changed and update only the changed objects. To build the foundation of the change detection algorithm for that, in this paper, we propose a change detection method combined with object classification. Despite its simplicity, the experiment showed promising results with an object detector fine-tuned with data from the target environment. Furthermore, with our clustering-based post-processing, false positives produced by the frame-wise change detection were observed to be successfully suppressed.
In this study, we have developed a novel method that enables the visualization of light rays in the air and interaction with these rays. In this method, the first step involves illuminating light rays in a space fille...
详细信息
ISBN:
(数字)9781510679931
ISBN:
(纸本)9781510679931;9781510679924
In this study, we have developed a novel method that enables the visualization of light rays in the air and interaction with these rays. In this method, the first step involves illuminating light rays in a space filled with mist to visualize the rays within the space. Subsequently, by applying a Micro Mirror Array Plate (MMAP) to the visualized rays, it becomes possible to visualize the light rays in the air without mist. Users can interact with the visualized light rays in the air by touching or moving them with their fingers.
Rotation gain is a crucial technique in Redirected Walking (RDW) for altering users' virtual trajectories. However, prior research [3] lacked a systematic exploration of how different visual characteristics impact...
详细信息
ISBN:
(纸本)9798350374490;9798350374506
Rotation gain is a crucial technique in Redirected Walking (RDW) for altering users' virtual trajectories. However, prior research [3] lacked a systematic exploration of how different visual characteristics impact users' perception of rotation speed. Therefore, this study proposes an investigation into this issue by designing eight VR scenes varying in visual density, spatial size, and realism. Through a within-subject study, the impact of these factors on the subjective detection of rotational speed was assessed. The results revealed significant differences in perceptual detection thresholds for rotation gains between room and landscape scenes, particularly in the lower bound of rotation gain thresholds.
Change detection(CD)is becoming indispensable for unmanned aerial vehicles(UAVs),especially in the domain of water landing,rescue and ***,even the most advanced models require large amounts of data for model training ...
详细信息
Change detection(CD)is becoming indispensable for unmanned aerial vehicles(UAVs),especially in the domain of water landing,rescue and ***,even the most advanced models require large amounts of data for model training and ***,sufficient labeled images with different imaging conditions are *** by computer graphics,we present a cloning method to simulate inland-water scene and collect an auto-labeled simulated *** simulated dataset consists of six challenges to test the effects of dynamic background,weather,and noise on change detection ***,we propose an image translation framework that translates simulated images to synthetic *** framework uses shared parameters(encoder and generator)and 22×22 receptive fields(discriminator)to generate realistic synthetic images as model training *** experimental results indicate that:1)different imaging challenges affect the performance of change detection models;2)compared with simulated images,synthetic images can effectively improve the accuracy of supervised models.
In recent years, much achievement have been made in the field of 3D clothed human reconstruction. However, most of researches performed not well for reconstruction from in-the-wild images due to the domain gap between...
详细信息
ISBN:
(纸本)9798350349405;9798350349399
In recent years, much achievement have been made in the field of 3D clothed human reconstruction. However, most of researches performed not well for reconstruction from in-the-wild images due to the domain gap between the synthetic images of training datasets and the in-the-wild images. In this study, a modular model, including clothes encoder, body encoder and cloth generator, is proposed to perform 3D clothed human reconstruction from one single-view in-the-wild RGB image. In particular, we introduce the adaptive aggregation of convolution and multi-head attention into the cloth encoder and apply the adjustment of the segmentation at the preprocessing stage. According to experiments on MSCOCO and 3DPW datasets, the proposed method achieves state-of-the-art performance on 3D clothed human reconstruction from in-the-wild images compared with previous works.
In task-oriented Augmented Reality (AR), humanoid Embodied Conversational Agents can enhance the feeling of social presence and reduce mental workload. Yet, such agents can also introduce social biases and lead to dis...
详细信息
ISBN:
(纸本)9798350374490;9798350374506
In task-oriented Augmented Reality (AR), humanoid Embodied Conversational Agents can enhance the feeling of social presence and reduce mental workload. Yet, such agents can also introduce social biases and lead to distractions. This presents a challenge for AR applications that require the user to concentrate mainly on a task environment. To address this, we introduce a non-humanoid virtual assistant designed for minimal visual intrusion in AR. Our approach aims to enhance a user's focus on the tasks they need to perform. We explain our design choices based on previously published guidelines and describe our prototype implemented for an optical-see-through headset.
暂无评论