View synthesis in the scattering medium faces challenges due to image degradation caused by medium scattering, and existing methods struggle to effectively address this issue. Although Neural Radiance Fields (NeRFs) excel in novel view synthesis and high-quality 3D reconstruction, they suffer from slow training speeds and poor handling of scenes with scattering. However, 3D Gaussian Splatting (3DGS) naturally exhibits sparsity, allowing for efficient representation of complex opaque geometries and surface details, but it is limited in modeling medium scattering. To address these limitations, we propose a novel method that combines the volumetric rendering strengths of NeRF with the sparse representation capabilities of 3DGS to effectively handle scattering media. By using 3DGS to represent objects and leveraging volumetric rendering for medium modeling, our method can mitigate the effects of medium scattering, rendering clear scenes in scattering media and synthesizing the appearance and depth of distant objects from novel viewpoints. The experimental results demonstrate a significant improvement in the performance of view-synthesis tasks, with an average increase of 3 to 4 dB. The rendering efficiency improved, with the training time reduced to 8 minutes, while preserving fine details.

Light field (LF) atmospheric descattering methods using multi-view images from camera arrays offer significant advantages for solving strong scattering due to their ability in exploiting high-dimensional light information. However, the relationship between performance and scattered LF sampling rate (i.e., the density of samples per unit area) is an unknown coupling, affecting acquisition and processing complexity. In this paper, we define the minimum atmospheric scattered LF sampling rate under optimal descattering quality, based on attenuated spectral support in scattering scenarios derived from the proposed atmospheric point spread function (APSF). The proposed APSF integrates the camera model, radiative transfer equation, and modified generalized Gaussian distribution (GGD) to describe multiple scattering. For any scattering parameters, the proposed APSF can be directly derived without infinite series, ensuring full adaptability to all acquisition systems through the integration of system model. Combining APSF with scene and acquisition system information, the scattered LF spectrum is determined, and consequently the minimum atmospheric scattered LF sampling rate is derived for the first time. Experimental results demonstrate the accuracy, effectiveness, and robustness of the proposed atmospheric scattered LF sampling theory through comparisons of atmospheric descattering performance across different LF sampling rates, object types, scene depths, and scattering intensities. The proposed method achieves a reduction in the number of acquisition cameras by an average of 78.4% while maintaining processing quality, which significantly enhances the applicability of LF atmospheric descattering methods.

Extrinsic calibration between LiDAR and camera has become an indispensable task across diverse domains, including autonomous vehicles, robotics, and surveillance systems. However, existing methods suffer from limited precision due to the inaccurate and insufficient detected features caused by the sparsity of point-clouds and the inherent ranging errors of LiDAR. In this paper, we propose a multi-dimensional geometric feature-based calibration method between LiDAR and camera. First, a 3D structured calibration target is proposed with multi-normal surfaces, edges in different directions, and distinctive corner features. Secondly, a point-plane and angle error-based point-cloud feature detection method is designed to establish 3D-2D feature point pairs with image features. Finally, a Perspective-n-Point (PnP) problem is solved to estimate the extrinsic parameters. The experimental results show that the proposed method reduces Mean Reprojection Error (MRE) by 0.05 pixels and achieves a 70% reduction in Normalized Reprojection Error (NRE) compared with state-of-the-art (SOTA) methods under the conditions of smaller training size, larger test size, and more repeat times.

Adverse weather introduces disruptive noise into LiDAR data within autonomous driving systems, compromising the accuracy and range of 3D perception. Mitigating this challenge for high-precision noise removal becomes intricate due to the varying noise distributions at different distances. A novel spatiotemporal denoising network, AdWeatherNet, is proposed to address this problem. The Spatial Encoder module dynamically encodes spatial features using a designed density evaluation model. Additionally, the Temporal Differential Attention module effectively leverages temporal variation in adjacent point clouds to identify and accurately remove noise. To drive the research, we also introduce an adverse weather dataset, named the AdScenes dataset, which features point-wise annotations and a wide variety of weather conditions, making it one of the largest comprehensive datasets in this domain. The experimental results demonstrate the effectiveness of our method, with a remarkable improvement of +9.5% of IoU in rainy scenes, +5.9% of IoU in snowy scenes, and +1.9% of IoU in foggy scenes. Compared to the SOTA, AdWeatherNet enhances the mAP of object detection by an average of +1.8% across all weather conditions. Our method contributes to the development of reliable LiDAR perception systems, fostering the development of autonomous vehicles.

Time-of-flight (ToF) devices have greatly propelled the advancement of various multi-modal perception applications. However, achieving accurate rendering of time-resolved information remains a challenge, particularly in scenes involving complex geometries, diverse materials and participating media. Existing ToF rendering works have demonstrated notable results, yet they struggle with scenes involving scattering media and camera-warped settings. Other steady-state volumetric rendering methods exhibit significant bias or variance when directly applied to ToF rendering tasks. To address these challenges, we integrate transient diffusion theory into path construction and propose novel sampling methods for free-path distance and scattering direction, via resampled importance sampling and offline tabulation. An elliptical sampling method is further adapted to provide controllable vertex connection satisfying any required photon traversal time. In contrast to the existing temporal uniform sampling strategy, our method is the first to consider the contribution of transient radiance to importance-sample the full path, and thus enables improved temporal path construction under multiple scattering settings. The proposed method can be integrated into both path tracing and photon-based frameworks, delivering significant improvements in quality and efficiency with at least a 5x MSE reduction versus SOTA methods in equal rendering time.