Related papers: Slanted Stixels: Representing San Francisco's Stee…
We introduce a new regression framework designed to deal with large-scale, complex data that lies around a low-dimensional manifold with noises. Our approach first constructs a graph representation, referred to as the skeleton, to capture…
Prosthetic vision is being applied to partially recover the retinal stimulation of visually impaired people. However, the phosphenic images produced by the implants have very limited information bandwidth due to the poor resolution and lack…
Accurate localization and mapping in outdoor environments remains challenging when using consumer-grade hardware, particularly with rolling-shutter cameras and low-precision inertial navigation systems (INS). We present a novel semantic…
Vehicle detection and localization in complex traffic scenarios pose significant challenges due to the interference of moving objects. Traditional methods often rely on outlier exclusions or semantic segmentations, which suffer from low…
Following the advent of NeRFs, 3D Gaussian Splatting (3D-GS) has paved the way to real-time neural rendering overcoming the computational burden of volumetric methods. Following the pioneering work of 3D-GS, several methods have attempted…
Contextual information can have a substantial impact on the performance of visual tasks such as semantic segmentation, object detection, and geometric estimation. Data stored in Geographic Information Systems (GIS) offers a rich source of…
This paper proposes a neural rendering approach that represents a scene as "compressed light-field tokens (CLiFTs)", retaining rich appearance and geometric information of a scene. CLiFT enables compute-efficient rendering by compressed…
Learning implicit representations has been a widely used solution for surface reconstruction from 3D point clouds. The latest methods infer a distance or occupancy field by overfitting a neural network on a single point cloud. However,…
Rendering volumetric scattering media, including clouds, fog, smoke, and other complex materials, is crucial for realism in computer graphics. Traditional path tracing, while unbiased, requires many long path samples to converge in scenes…
Combining accurate geometry with rich semantics has been proven to be highly effective for language-guided robotic manipulation. Existing methods for dynamic scenes either fail to update in real-time or rely on additional depth sensors for…
Place recognition gives a SLAM system the ability to correct cumulative errors. Unlike images that contain rich texture features, point clouds are almost pure geometric information which makes place recognition based on point clouds…
Shape priors learned from data are commonly used to reconstruct 3D objects from partial or noisy data. Yet no such shape priors are available for indoor scenes, since typical 3D autoencoders cannot handle their scale, complexity, or…
We present a novel method for accurate and efficient up- sampling of sparse depth data, guided by high-resolution imagery. Our approach goes beyond the use of intensity cues only and additionally exploits object boundary cues through…
We propose SNI-SLAM, a semantic SLAM system utilizing neural implicit representation, that simultaneously performs accurate semantic mapping, high-quality surface reconstruction, and robust camera tracking. In this system, we introduce…
Reconstructing urban street scenes is crucial due to its vital role in applications such as autonomous driving and urban planning. These scenes are characterized by long and narrow camera trajectories, occlusion, complex object…
Challenging to capture, and challenging to display on a cellphone screen, the panorama paradoxically remains both a staple and underused feature of modern mobile camera applications. In this work we address both of these challenges with a…
In crowded urban environments where traffic is dense, current technologies struggle to oversee tight navigation, but surface-level understanding allows autonomous vehicles to safely assess proximity to surrounding obstacles. 3D or 2D scene…
Dynamic scene rendering opens new avenues in autonomous driving by enabling closed-loop simulations with photorealistic data, which is crucial for validating end-to-end algorithms. However, the complex and highly dynamic nature of traffic…
To bridge the semantic gap between vision and language (VL), it is necessary to develop a good alignment strategy, which includes handling semantic diversity, abstract representation of visual information, and generalization ability of…
Monocular depth estimation involves predicting depth from a single RGB image and plays a crucial role in applications such as autonomous driving, robotic navigation, 3D reconstruction, etc. Recent advancements in learning-based methods have…