Related papers: DVGT: Driving Visual Geometry Transformer
In this paper, we study the problem of 3D scene geometry decomposition and manipulation from 2D views. By leveraging the recent implicit neural representation techniques, particularly the appealing neural radiance fields, we introduce an…
In this work, we introduce Vision-Language Generative Pre-trained Transformer (VL-GPT), a transformer model proficient at concurrently perceiving and generating visual and linguistic data. VL-GPT achieves a unified pre-training approach for…
Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of domains including spatial intelligence, embodied intelligence, and autonomous driving. While…
Determining the relative pose of a previously unseen object between two images is pivotal to the success of generalizable object pose estimation. Existing approaches typically predict 3D translation utilizing the ground-truth object…
In recent years, self-supervised methods for monocular depth estimation has rapidly become an significant branch of depth estimation task, especially for autonomous driving applications. Despite the high overall precision achieved, current…
Traditional monocular direct visual odometry (DVO) is one of the most famous methods to estimate the ego-motion of robots and map environments from images simultaneously. However, DVO heavily relies on high-quality images and accurate…
We propose a novel method to estimate a driver's points-of-gaze using a pair of ordinary cameras mounted on the windshield and dashboard of a car. This is a challenging problem due to the dynamics of traffic environments with 3D scenes of…
With the growing adoption of vision-language-action models and world models in autonomous driving systems, scalable image tokenization becomes crucial as the interface for the visual modality. However, most existing tokenizers are designed…
Cross-subject motor-imagery decoding remains a major challenge in EEG-based brain-computer interfaces. To mitigate strong inter-subject variability, recent work has emphasized manifold-based approaches operating on covariance…
Transformers have recently shown superior performances on various vision tasks. The large, sometimes even global, receptive field endows Transformer models with higher representation power over their CNN counterparts. Nevertheless, simply…
Multi-camera 3D object detection for autonomous driving is a challenging problem that has garnered notable attention from both academia and industry. An obstacle encountered in vision-based techniques involves the precise extraction of…
Feature learning for 3D object detection from point clouds is very challenging due to the irregularity of 3D point cloud data. In this paper, we propose Pointformer, a Transformer backbone designed for 3D point clouds to learn features…
We present DriveGen3D, a novel framework for generating high-quality and highly controllable dynamic 3D driving scenes that addresses critical limitations in existing methodologies. Current approaches to driving scene synthesis either…
A 360{\deg} perception of scene geometry is essential for automated driving, notably for parking and urban driving scenarios. Typically, it is achieved using surround-view fisheye cameras, focusing on the near-field area around the vehicle.…
Despite the recent success of Neural Radiance Field (NeRF), it is still challenging to render large-scale driving scenes with long trajectories, particularly when the rendering quality and efficiency are in high demand. Existing methods for…
Depth estimation, visual odometry (VO), and bird's-eye-view (BEV) scene layout estimation present three critical tasks for driving scene perception, which is fundamental for motion planning and navigation in autonomous driving. Though they…
We present DrivingGaussian++, an efficient and effective framework for realistic reconstructing and controllable editing of surrounding dynamic autonomous driving scenes. DrivingGaussian++ models the static background using incremental 3D…
Generating novel views of a natural scene, e.g., every-day scenes both indoors and outdoors, from a single view is an under-explored problem, even though it is an organic extension to the object-centric novel view synthesis. Existing…
Real-world robots localize objects from natural-language instructions while scenes around them keep changing. Yet most of the existing 3D visual grounding (3DVG) method still assumes a reconstructed and up-to-date point cloud, an assumption…
When solving inverse problems in geophysical imaging, deep generative models (DGMs) may be used to enforce the solution to display highly structured spatial patterns which are supported by independent information (e.g. the geological…