Related papers: VIBUS: Data-efficient 3D Scene Parsing with VIewpo…

Contrastive Language-Image Pre-training (CLIP) achieves promising results in 2D zero-shot and few-shot learning. Despite the impressive performance in 2D, applying CLIP to help the learning in 3D scene understanding has yet to be explored.…

Holistically understanding an object and its 3D movable parts through visual perception models is essential for enabling an autonomous agent to interact with the world. For autonomous driving, the dynamics and states of vehicle parts such…

We propose a novel scene flow method that captures 3D motions from point clouds without relying on ground-truth scene flow annotations. Due to the irregularity and sparsity of point clouds, it is expensive and time-consuming to acquire…

Machine Learning often involves various imprecise labels, leading to diverse weakly supervised settings. While recent methods aim for universal handling, they usually suffer from complex manual pre-work, ignore the relationships between…

Training deep neural networks to estimate the viewpoint of objects requires large labeled training datasets. However, manually labeling viewpoints is notoriously hard, error-prone, and time-consuming. On the other hand, it is relatively…

Recently, 3D Gaussian Splatting (3DGS) has excelled in novel view synthesis (NVS) with its real-time rendering capabilities and superior quality. However, it encounters challenges for high-resolution novel view synthesis (HRNVS) due to the…

In autonomous driving, LiDAR sensors are vital for acquiring 3D point clouds, providing reliable geometric information. However, traditional sampling methods of preprocessing often ignore semantic features, leading to detail loss and ground…

The growing scale of datasets in deep learning has introduced significant computational challenges. Dataset pruning addresses this challenge by constructing a compact but informative coreset from the full dataset with comparable…

In recent times, there has been a notable surge in multimodal approaches that decorates raw LiDAR point clouds with camera-derived features to improve object detection performance. However, we found that these methods still grapple with the…

Instance shadow detection, crucial for applications such as photo editing and light direction estimation, has undergone significant advancements in predicting shadow instances, object instances, and their associations. The extension of this…

We propose a new self-supervised method for pre-training the backbone of deep perception models operating on point clouds. The core idea is to train the model on a pretext task which is the reconstruction of the surface on which the 3D…

In the field of autonomous driving, self-training is widely applied to mitigate distribution shifts in LiDAR-based 3D object detectors. This eliminates the need for expensive, high-quality labels whenever the environment changes (e.g.,…

3D understanding is a key capability for real-world AI assistance. High-quality data plays an important role in driving the development of the 3D understanding community. Current 3D scene understanding datasets often provide geometric and…

Monocular 3D object detection typically relies on pseudo-labeling techniques to reduce dependency on real-world annotations. Recent advances demonstrate that deterministic linguistic cues can serve as effective auxiliary weak supervision…

Bridging natural language and 3D geometry is a crucial step toward flexible, language-driven scene understanding. While recent advances in 3D Gaussian Splatting (3DGS) have enabled fast and high-quality scene reconstruction, research has…

Collecting and labeling the registered 3D point cloud is costly. As a result, 3D resources for training are typically limited in quantity compared to the 2D images counterpart. In this work, we deal with the data scarcity challenge of 3D…

In this paper, we investigate the use of diffusion models which are pre-trained on large-scale image-caption pairs for open-vocabulary 3D semantic understanding. We propose a novel method, namely Diff2Scene, which leverages frozen…

3D semantic segmentation is one of the most crucial tasks in driving perception. The ability of a learning-based model to accurately perceive dense 3D surroundings often ensures the safe operation of autonomous vehicles. However, existing…

Semi-supervised 3D object detection is a promising yet under-explored direction to reduce data annotation costs, especially for cluttered indoor scenes. A few prior works, such as SESS and 3DIoUMatch, attempt to solve this task by utilizing…

We propose ViewAL, a novel active learning strategy for semantic segmentation that exploits viewpoint consistency in multi-view datasets. Our core idea is that inconsistencies in model predictions across viewpoints provide a very reliable…