Related papers: Physically Based Neural LiDAR Resimulation

Non-line-of-sight (NLOS) imaging is based on capturing the multi-bounce indirect reflections from the hidden objects. Active NLOS imaging systems rely on the capture of the time of flight of light through the scene, and have shown great…

Recent neural rendering and reconstruction techniques, such as NeRFs or Gaussian Splatting, have shown remarkable novel view synthesis capabilities but require hundreds of images of the scene from diverse viewpoints to render high-quality…

Neural rendering-based urban scene reconstruction methods commonly rely on images collected from driving vehicles with cameras facing and moving forward. Although these methods can successfully synthesize from views similar to training…

Computational approach to imaging around the corner, or non-line-of-sight (NLOS) imaging, is becoming a reality thanks to major advances in imaging hardware and reconstruction algorithms. A recent development towards practical NLOS imaging,…

Perception in 3D has become standard practice for a large part of robotics applications. High quality 3D perception is costly. Our previous work on a nodding 2D Lidar provides high quality 3D depth information with low cost, but the sparse…

Capturing high-quality photographs under diverse real-world lighting conditions is challenging, as both natural lighting (e.g., low-light) and camera exposure settings (e.g., exposure time) significantly impact image quality. This challenge…

In real-world road scenes, diverse material properties lead to complex light reflection phenomena, making accurate color reproduction crucial for enhancing the realism and safety of simulated driving environments. However, existing methods…

Near infrared (NIR) to Visible (VIS) face matching is challenging due to the significant domain gaps as well as a lack of sufficient data for cross-modality model training. To overcome this problem, we propose a novel method for paired…

For robust visual-inertial SLAM in perceptually-challenging indoor environments,recent studies exploit line features to extract descriptive information about scene structure to deal with the degeneracy of point features. But existing…

By harnessing the potent generative capabilities of pre-trained large video diffusion models, we propose NVS-Solver, a new novel view synthesis (NVS) paradigm that operates \textit{without} the need for training. NVS-Solver adaptively…

Sensor simulation is a key component for testing the performance of self-driving vehicles and for data augmentation to better train perception systems. Typical approaches rely on artists to create both 3D assets and their animations to…

In this paper we reexamine the process through which a Neural Radiance Field (NeRF) can be trained to produce novel LiDAR views of a scene. Unlike image applications where camera pixels integrate light over time, LiDAR pulses arrive at…

Generating novel views of an object from a single image is a challenging task. It requires an understanding of the underlying 3D structure of the object from an image and rendering high-quality, spatially consistent new views. While recent…

Lithography simulation is a critical step in VLSI design and optimization for manufacturability. Existing solutions for highly accurate lithography simulation with rigorous models are computationally expensive and slow, even when equipped…

High-resolution LiDAR data plays a critical role in 3D semantic segmentation for autonomous driving, but the high cost of advanced sensors limits large-scale deployment. In contrast, low-cost sensors such as 16-channel LiDAR produce sparse…

LiDARs are widely used for 3D depth reconstruction, but their performance is often limited by inherent hardware constraints that impose trade-offs between range, spatial resolution, and frame rate. Many LiDAR systems typically operate at…

We address a data augmentation problem for LiDAR. Given a LiDAR scan of a scene from some position, how can one simulate new scans of that scene from different, secondary positions? The method defines criteria for selecting valid secondary…

Reconstructing photo-realistic large-scale scenes from images, for example at city scale, is a long-standing problem in computer graphics. Neural rendering is an emerging technique that enables photo-realistic image synthesis from…

As Neural Radiance Field (NeRF) implementations become faster, more efficient and accurate, their applicability to real world mapping tasks becomes more accessible. Traditionally, 3D mapping, or scene reconstruction, has relied on expensive…

NeRF provides unparalleled fidelity of novel view synthesis: rendering a 3D scene from an arbitrary viewpoint. NeRF requires training on a large number of views that fully cover a scene, which limits its applicability. While these issues…