34 accepted papers
This work focuses on modeling dynamic urban environments for autonomous driving simulation. Contemporary data-driven methods using neural radiance fields have achieved photorealistic driving scene modeling, but they suffer from low rendering efficacy. Recently, some approaches have explored 3D Gauss…
Vision-based autonomous driving has gained much attention due to its low costs and excellent performance. Compared with dense BEV (Bird's Eye View) or sparse query models, Gaussian-centric method is a comprehensive yet sparse representation by describing scene with 3D semantic Gaussians. In this pap
Existing 3D point tracking methods mostly rely on heuristic designs or scene reconstruction, which incurs significant computational overhead and makes it difficult to meet the demands of real-time applications. To address this problem, in this work, we present a novel spatial tracker that leverages
This work focuses on the problem of 6D pose estimation for novel objects when a reference 3D model or posed reference images are not available. While existing methods can estimate the precise 6D pose of objects, they heavily rely on curated CAD models or reference images, the preparation of which is…
This paper focuses on scene reconstruction under nighttime conditions in autonomous driving simulation. Recent methods based on Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) have achieved photorealistic modeling in autonomous driving scene reconstruction, but they primarily focus o…
Recent years have witnessed remarkable progress in world models, which primarily aim to capture the spatiotemporal correlations between an agent's actions and the evolving environment. However, existing approaches often suffer from tight runtime coupling or depend on offline reward signals, resultin
Realistic scene reconstruction and view synthesis are essential for advancing autonomous driving systems by simulating safety-critical scenarios. 3D Gaussian Splatting (3DGS) excels in real-time rendering and static scene reconstructions but struggles with modeling driving scenarios due to complex b
Novel view synthesis of urban scenes is essential for autonomous driving-related applications. Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization. We introduce EVolSplat, an efficient 3D Gaussian Splatting model…
This work focuses on the problem of 6D pose estimation for novel objects when a reference 3D model or posed reference images are not available. While existing methods can estimate the precise 6D pose of objects, they heavily rely on curated CAD models or reference images, the preparation of which is
Leveraging the visual priors of pre-trained text-to-image diffusion models offers a promising solution to enhance zero-shot generalization in dense prediction tasks. However, existing methods often uncritically use the original diffusion formulation, which may not be optimal due to the fundamental d…
Large Language Models (LLMs) have made substantial advancements in the field of robotic and autonomous driving. This study presents the first Occupancy-based Large Language Model (Occ-LLM), which represents a pioneering effort to integrate LLMs with an important representation. To effectively encode
End-to-end autonomous driving systems, predominantly trained through imitation learning, have demonstrated considerable effectiveness in leveraging large-scale expert driving data. Despite their success in open-loop evaluations, these systems often exhibit significant performance degradation in clos…
Sparse Perception Models (SPMs) adopt a query-driven paradigm that forgoes explicit dense BEV or volumetric construction, enabling highly efficient computation and accelerated inference. In this paper, we introduce SQS, a novel query-based splatting pre-training specifically designed to advance SPMs…
Estimating the 6D pose of novel objects is a fundamental yet challenging problem in robotics, often relying on access to object CAD models. However, acquiring such models can be costly and impractical. Recent approaches aim to bypass this requirement by leveraging strong priors from founda…
This paper introduces VisionPAD, a novel self-supervised pre-training paradigm designed for vision-centric algorithms in autonomous driving. In contrast to previous approaches that employ neural rendering with explicit depth supervision, VisionPAD utilizes more efficient 3D Gaussian Splatting to rec…
Holistic understanding of urban scenes based on RGB images is a challenging yet important problem. It encompasses understanding both the geometry and appearance to enable novel view synthesis parsing semantic labels and tracking moving objects. Despite considerable progress existing approaches often…
3D occupancy prediction is an emerging task that aims to estimate the occupancy states and semantics of 3D scenes using multi-view images. However, image-based scene perception encounters significant challenges in achieving accurate prediction due to the absence of geometric priors. In this paper, w…
Range-View(RV)-based 3D point cloud segmentation is widely adopted due to its compact data form. However, RV-based methods fall short in providing robust segmentation for the occluded points and suffer from distortion of projected RGB images due to the sparse nature of 3D point clouds. To alleviate…
A fast and accurate panoptic segmentation system for LiDAR point clouds is crucial for autonomous driving vehicles to understand the surrounding objects and scenes. Existing approaches usually rely on proposals or clustering to segment foreground instances. As a result, they struggle to achieve real…
Reconstructing 3D vehicles from noisy and sparse partial point clouds is of great significance to autonomous driving. Most existing 3D reconstruction methods cannot be directly applied to this problem because they are elaborately designed to deal with dense inputs with trivial noise. In this work, w…
Neural radiance fields (NeRF) achieve impressive performance in novel view synthesis when trained on only single sequence data. However, leveraging multiple sequences captured by different cameras at different times is essential for better reconstruction performance. Multi-sequence data takes two ma…
We present NeRFVS, a novel neural radiance fields (NeRF) based method to enable free navigation in a room. NeRF achieves impressive performance in rendering images for novel views similar to the input views while suffering for novel views that are significantly different from the training views. To…
Data is a fundamental building block for LiDAR perception systems. Unfortunately, real-world data collection and annotation is extremely costly & laborious. Recently, real data based LiDAR simulators have shown tremendous potential to complement real data, due to their scalability and high-fidelity
Contemporary LiDAR-based 3D object detection methods mostly focus on single-domain learning or cross-domain adaptive learning. However, for autonomous driving systems, optimizing a specific LiDAR-based 3D object detector for each domain is costly and lacks of scalability in real-world deployment. It…
3D object detection using LiDAR data is an indispensable component for autonomous driving systems. Yet, only a few LiDAR-based 3D object detection methods leverage segmentation information to further guide the detection process. In this paper, we propose a novel multi-task framework that jointly per…
Curbs are one of the essential elements of urban and highway traffic environments. Robust curb detection provides road structure information for motion planning in an autonomous driving system. Commonly, video cameras and 3D LiDARs are mounted on autonomous vehicles for curb detection. However, came…
Panoptic segmentation aims to address semantic and instance segmentation simultaneously in a unified framework. However, an efficient solution of panoptic segmentation in applications like autonomous driving is still an open research problem. In this work, we propose a novel LiDAR-based panoptic sys…
In this paper, we focus on a less explored, but more realistic and complex problem of domain adaptation in LiDAR semantic segmentation. There is a significant drop in performance of an existing segmentation model when training (source domain) and testing (target domain) data originate from different…
Autonomous robotic systems and self driving cars rely on accurate perception of their surroundings as the safety of the passengers and pedestrians is the top priority. Semantic segmentation is one the essential components of environmental perception that provides semantic information of the scene. R…
he success of supervised LiDAR perception methods relies on the availability of large sets of labeled point cloud data, for which the labeling process is costly and time consuming. Given unpaired LiDAR datasets of similar sizes from two domains, with one (source) containing task-specific labels e.g.
Deterministic down-sampling of an unordered point cloud in a deep neural network has not been rigorously studied so far. Existing methods down-sample the points regardless of their importance for the network output and often address down-sampling the raw point cloud before processing. As a result, s…
Three-dimensional feature descriptors are heavily employed in various 3-D perception applications to find keypoint correspondences between two point clouds. The availability of mobile devices equipped with depth sensors compels the developed applications to be both memory and computationally efficie
This letter proposes a robust vehicle localization method based on a prior point cloud in urban area. The high resolution point cloud collected six months ago is provided from Singapore Land Authority around One-north area in Singapore, because the data are outdated there are many changed aspects of
In this paper, we introduce the very first ‘binary’ 3D feature descriptor, B-SHOT, for fast and efficient keypoint matching on 3D point clouds. We propose a binary quantization method that converts a real valued vector to a binary vector. We apply this method on a state-of-the-art 3D feature descrip…