Related papers: GaussianFlowOcc: Sparse and Weakly Supervised Occu…
We present GaSpCT, a novel view synthesis and 3D scene representation method used to generate novel projection views for Computer Tomography (CT) scans. We adapt the Gaussian Splatting framework to enable novel view synthesis in CT based on…
Creating 4D fields of Gaussian Splatting from images or videos is a challenging task due to its under-constrained nature. While the optimization can draw photometric reference from the input videos or be regulated by generative models,…
3D instance segmentation, with a variety of applications in robotics and augmented reality, is in large demands these days. Unlike 2D images that are projective observations of the environment, 3D models provide metric reconstruction of the…
Semantic and panoptic occupancy prediction for road scene analysis provides a dense 3D representation of the ego vehicle's surroundings. Current camera-only approaches typically rely on costly dense 3D supervision or require training models…
Novel view synthesis of dynamic scenes has been an intriguing yet challenging problem. Despite recent advancements, simultaneously achieving high-resolution photorealistic results, real-time rendering, and compact storage remains a…
Reliably predicting future occupancy of highly dynamic urban environments is an important precursor for safe autonomous navigation. Common challenges in the prediction include forecasting the relative position of other vehicles, modelling…
3D occupancy prediction has attracted much attention in the field of autonomous driving due to its powerful geometric perception and object recognition capabilities. However, existing methods have not explored the most essential…
Optical flow, or the estimation of motion fields from image sequences, is one of the fundamental problems in computer vision. Unlike most pixel-wise tasks that aim at achieving consistent representations of the same category, optical flow…
We introduce LOcc, an effective and generalizable framework for open-vocabulary occupancy (OVO) prediction. Previous approaches typically supervise the networks through coarse voxel-to-text correspondences via image features as…
Occupancy mapping has been a key enabler of mobile robotics. Originally based on a discrete grid representation, occupancy mapping has evolved towards continuous representations that can predict the occupancy status at any location and…
Embodied 3D Semantic Scene Completion (SSC) infers dense geometry and semantics from continuous egocentric observations. Most existing Gaussian-based methods rely on random initialization of many primitives within predefined spatial bounds,…
Dense 3D semantic occupancy perception is critical for mobile robots operating in pedestrian-rich environments, yet it remains underexplored compared to its application in autonomous driving. To address this gap, we present MobileOcc, a…
Monocular 3D Semantic Scene Completion (SSC) is a challenging yet promising task that aims to infer dense geometric and semantic descriptions of a scene from a single image. While recent object-centric paradigms significantly improve…
3D Semantic Scene Completion (SSC) provides comprehensive scene geometry and semantics for autonomous driving perception, which is crucial for enabling accurate and reliable decision-making. However, existing SSC methods are limited to…
As a novel 3D scene representation, semantic occupancy has gained much attention in autonomous driving. However, existing occupancy prediction methods mainly focus on designing better occupancy representations, such as tri-perspective view…
Reconstructing continuous flow fields from sparse surface-mounted sensors is central to aerodynamic design, flow control, and digital-twin instrumentation. Existing neural methods for this task typically encode sensor readings into implicit…
3D Gaussian Splatting (3DGS) has gained significant attention for its real-time, photo-realistic rendering in novel-view synthesis and 3D modeling. However, existing methods struggle with accurately modeling in-the-wild scenes affected by…
The prediction of 3D semantic occupancy enables autonomous vehicles (AVs) to perceive the fine-grained geometric and semantic scene structure for safe navigation and decision-making. Existing methods mainly rely on either voxel-based…
3D Gaussian Splatting represents a breakthrough in the field of novel view synthesis. It establishes Gaussians as core rendering primitives for highly accurate real-world environment reconstruction. Recent advances have drastically…
Point clouds are crucial for capturing three-dimensional data but often suffer from incompleteness due to limitations such as resolution and occlusion. Traditional methods typically rely on point-based approaches within discriminative…