Related papers: LightOctree: Lightweight 3D Spatially-Coherent Ind…

3D occupancy prediction has recently emerged as a new paradigm for holistic 3D scene understanding and provides valuable information for downstream planning in autonomous driving. Most existing methods, however, are computationally…

Volumetric rendering has become central to modern novel view synthesis methods, which use differentiable rendering to optimize 3D scene representations directly from observed views. While many recent works build on NeRF or 3D Gaussians, we…

Efficiently calculating global illumination has always been one of the greatest challenges in computer graphics. Algorithms for approximating global illumination have always struggled to run in realtime for fully dynamic scenes, and have…

This paper proposes a method to reconstruct the neural radiance field with equirectangular omnidirectional images. Implicit neural scene representation with a radiance field can reconstruct the 3D shape of a scene continuously within a…

The lack of labeled datasets in 3D vision for surgical scenes inhibits the development of robust 3D reconstruction algorithms in the medical domain. Despite the popularity of Neural Radiance Fields and 3D Gaussian Splatting in the general…

A unified neural network structure is presented for joint 3D object detection and point cloud segmentation in this paper. We leverage rich supervision from both detection and segmentation labels rather than using just one of them. In…

Reliable perception of the environment plays a crucial role in enabling efficient self-driving vehicles. Therefore, the perception system necessitates the acquisition of comprehensive 3D data regarding the surrounding objects within a…

Volumetry is one of the principal downstream applications of 3D medical image segmentation, for example, to detect abnormal tissue growth or for surgery planning. Conformal Prediction is a promising framework for uncertainty quantification,…

Estimating the layout of a room from a single-shot panoramic image is important in virtual/augmented reality and furniture layout simulation. This involves identifying three-dimensional (3D) geometry, such as the location of corners and…

Compact and accurate representations of 3D shapes are central to many perception and robotics tasks. State-of-the-art learning-based methods can reconstruct single objects but scale poorly to large datasets. We present a novel recursive…

Modern approaches for vision-centric environment perception for autonomous navigation make extensive use of self-supervised monocular depth estimation algorithms that output disparity maps. However, when this disparity map is projected onto…

Homography estimation is often an indispensable step in many computer vision tasks. The existing approaches, however, are not robust to illumination and/or larger viewpoint changes. In this paper, we propose bidirectional implicit…

Edge computing-based 3D perception has received attention in intelligent transportation systems (ITS) because real-time monitoring of traffic candidates potentially strengthens Vehicle-to-Everything (V2X) orchestration. Thanks to the…

We present a novel algorithm for light source estimation in scenes reconstructed with a RGB-D camera based on an analytically-derived formulation of path-tracing. Our algorithm traces the reconstructed scene with a custom path-tracer and…

Monocular normal estimation aims to estimate the normal map from a single RGB image of an object under arbitrary lights. Existing methods rely on deep models to directly predict normal maps. However, they often suffer from 3D misalignment:…

We present a method for relighting 3D reconstructions of large room-scale environments. Existing solutions for 3D scene relighting often require solving under-determined or ill-conditioned inverse rendering problems, and are as such unable…

Most indoor 3D scene reconstruction methods focus on recovering 3D geometry and scene layout. In this work, we go beyond this to propose PhotoScene, a framework that takes input image(s) of a scene along with approximately aligned CAD…

We present a learning-based technique for estimating high dynamic range (HDR), omnidirectional illumination from a single low dynamic range (LDR) portrait image captured under arbitrary indoor or outdoor lighting conditions. We train our…

One major goal of vision is to infer physical models of objects, surfaces, and their layout from sensors. In this paper, we aim to interpret indoor scenes from one RGBD image. Our representation encodes the layout of walls, which must…

Creating an appearance-preserving level-of-detail (LoD) representation for arbitrary 3D scenes is a challenging problem. The appearance of a scene is an intricate combination of both geometry and material models, and is further complicated…