Related papers: Veila: Panoramic LiDAR Generation from a Monocular…

Generative modeling of 3D LiDAR data is an emerging task with promising applications for autonomous mobile robots, such as scalable simulation, scene manipulation, and sparse-to-dense completion of LiDAR point clouds. While existing…

Autonomous agile robots need more than metric geometry: they must understand objects, rooms, places, and spatial relations for search, inspection, exploration, and human robot interaction. Conventional metric maps support localization and…

Video Diffusion Models (VDMs) have demonstrated remarkable capabilities in synthesizing realistic videos by learning from large-scale data. Although vanilla Low-Rank Adaptation (LoRA) can learn specific spatial or temporal movement to…

Diffusion models have achieved remarkable progress in video generation, but their controllability remains a major limitation. Key scene factors such as layout, lighting, and camera trajectory are often entangled or only weakly modeled,…

We report Zero123++, an image-conditioned diffusion model for generating 3D-consistent multi-view images from a single input view. To take full advantage of pretrained 2D generative priors, we develop various conditioning and training…

Integrating LiDAR and camera information in the bird's eye view (BEV) representation has demonstrated its effectiveness in 3D object detection. However, because of the fundamental disparity in geometric accuracy between these sensors,…

This paper presents a compact and accurate representation of 3D scenes that are observed by a LiDAR sensor and a monocular camera. The proposed method is based on the well-established Stixel model originally developed for stereo vision…

The increasing adoption of human-robot interaction presents opportunities for technology to positively impact lives, particularly those with visual impairments, through applications such as guide-dog-like assistive robotics. We present a…

This work presents Controllable Layer Decomposition (CLD), a method for achieving fine-grained and controllable multi-layer separation of raster images. In practical workflows, designers typically generate and edit each RGBA layer…

3D object detection has become an emerging task in autonomous driving scenarios. Previous works process 3D point clouds using either projection-based or voxel-based models. However, both approaches contain some drawbacks. The voxel-based…

Monocular depth estimation is a fundamental yet challenging task in computer vision, especially under complex conditions such as textureless surfaces, transparency, and specular reflections. Recent diffusion-based approaches have…

3D scene perception demands a large amount of adverse-weather LiDAR data, yet the cost of LiDAR data collection presents a significant scaling-up challenge. To this end, a series of LiDAR simulators have been proposed. Yet, they can only…

We propose pix2pix3D, a 3D-aware conditional generative model for controllable photorealistic image synthesis. Given a 2D label map, such as a segmentation or edge map, our model learns to synthesize a corresponding image from different…

Deep learning models for self-driving cars require a diverse training dataset to manage critical driving scenarios on public roads safely. This includes having data from divergent trajectories, such as the oncoming traffic lane or…

We study an important, yet largely unexplored problem of large-scale cross-modal visual localization by matching ground RGB images to a geo-referenced aerial LIDAR 3D point cloud (rendered as depth images). Prior works were demonstrated on…

Steering estimation is a critical task in autonomous driving, traditionally relying on 2D image-based models. In this work, we explore the advantages of incorporating 3D spatial information through hybrid architectures that combine 3D…

Controllable image synthesis, which enables fine-grained control over generated outputs, has emerged as a key focus in visual generative modeling. However, controllable generation remains challenging for Visual Autoregressive (VAR) models…

LiDAR segmentation has emerged as an important task to enrich scene perception and understanding. Range-view-based methods have gained popularity due to their high computational efficiency and compatibility with real-time deployment.…

Sparse LiDAR point clouds cause severe loss of detail of static structures and reduce the density of static points available for navigation. Reduced density can be detrimental to navigation under several scenarios. We observe that despite…

Synthesizing high-fidelity and controllable 4D LiDAR data is crucial for creating scalable simulation environments for autonomous driving. This task is inherently challenging due to the sensor's unique spherical geometry, the temporal…