Related papers: U4D: Uncertainty-Aware 4D World Modeling from LiDA…

LiDAR scene generation is critical for mitigating real-world LiDAR data collection costs and enhancing the robustness of downstream perception tasks in autonomous driving. However, existing methods commonly struggle to capture geometric…

In this paper, we present an active exploration framework for high-fidelity 3D reconstruction that incrementally builds a multi-level uncertainty space and selects next-best-views through an uncertainty-driven motion planner. We introduce a…

World models aim to endow AI systems with the ability to represent, generate, and interact with dynamic environments in a coherent and temporally consistent manner. While recent video generation models have demonstrated impressive visual…

Current generative models struggle to synthesize dynamic 4D driving scenes that simultaneously support temporal extrapolation and spatial novel view synthesis (NVS) without per-scene optimization. A key challenge lies in finding an…

3D object reconstruction is important for semantic scene understanding. It is challenging to reconstruct detailed 3D shapes from monocular images directly due to a lack of depth information, occlusion and noise. Most current methods…

LiDAR provides accurate geometric measurements of the 3D world. Unfortunately, dense LiDARs are very expensive and the point clouds captured by low-beam LiDAR are often sparse. To address these issues, we present UltraLiDAR, a data-driven…

We present SS4D, a native 4D generative model that synthesizes dynamic 3D objects directly from monocular video. Unlike prior approaches that construct 4D representations by optimizing over 3D or video generative models, we train a…

Recent advances in generative video models have led to significant breakthroughs in high-fidelity video synthesis, specifically in controllable video generation where the generated video is conditioned on text and action inputs, e.g., in…

3D laser scanning by LiDAR sensors plays an important role for mobile robots to understand their surroundings. Nevertheless, not all systems have high resolution and accuracy due to hardware limitations, weather conditions, and so on.…

LiDAR scene generation is increasingly important for scalable simulation and synthetic data creation, especially under diverse sensing conditions that are costly to capture at scale. Typically, diffusion-based LiDAR generators are developed…

Remarkable advances in recent 2D image and 3D shape generation have induced a significant focus on dynamic 4D content generation. However, previous 4D generation methods commonly struggle to maintain spatial-temporal consistency and adapt…

Recent techniques for text-to-4D generation synthesize dynamic 3D scenes using supervision from pre-trained text-to-video models. However, existing representations for motion, such as deformation models or time-dependent neural…

LiDAR-camera fusion enhances 3D panoptic segmentation by leveraging camera images to complement sparse LiDAR scans, but it also introduces a critical failure mode. Under adverse conditions, degradation or failure of the camera sensor can…

Despite the impressive progress on understanding and generating images shown by the recent unified architectures, the integration of 3D tasks remains challenging and largely unexplored. In this paper, we introduce UniUGG, the first unified…

We propose LiDAL, a novel active learning method for 3D LiDAR semantic segmentation by exploiting inter-frame uncertainty among LiDAR frames. Our core idea is that a well-trained model should generate robust results irrespective of…

Diffusion models (DMs) excel in photo-realistic image synthesis, but their adaptation to LiDAR scene generation poses a substantial hurdle. This is primarily because DMs operating in the point space struggle to preserve the curve-like…

State-of-the-art lidar place recognition models exhibit unreliable performance when tested on environments different from their training dataset, which limits their use in complex and evolving environments. To address this issue, we…

High-quality 4D reconstruction enables photorealistic and immersive rendering of the dynamic real world. However, unlike static scenes that can be fully captured with a single camera, high-quality dynamic scenes typically require dense…

World-model-based imagine-then-act becomes a promising paradigm for robotic manipulation, yet existing approaches typically support either purely image-based forecasting or reasoning over partial 3D geometry, limiting their ability to…

Combining 3D Gaussian splatting with Simultaneous Localization and Mapping (SLAM) has gained popularity as it enables continuous 3D environment reconstruction during motion. However, existing methods struggle in dynamic environments,…