Related papers: PUMPS: Skeleton-Agnostic Point-based Universal Mot…
Video anomaly detection has great potential in enhancing safety in the production and monitoring of crucial areas. Currently, most video anomaly detection methods are based on RGB modality, but its redundant semantic information may breach…
Point cloud completion aims to recover raw point clouds captured by scanners from partial observations caused by occlusion and limited view angles. This makes it hard to recover details because the global feature is unlikely to capture the…
With the capacity of modeling long-range dependencies in sequential data, transformers have shown remarkable performances in a variety of generative tasks such as image, audio, and text generation. Yet, taming them in generating less…
The ability to extrapolate dynamic 3D scenes beyond the observed timeframe is fundamental to advancing physical world understanding and predictive modeling. Existing dynamic 3D reconstruction methods have achieved high-fidelity rendering of…
We present Unified PDE Solvers (UPS), a data- and compute-efficient approach to developing unified neural operators for diverse families of spatiotemporal PDEs from various domains, dimensions, and resolutions. UPS embeds different PDEs…
3D dynamic point cloud (DPC) compression relies on mining its temporal context, which faces significant challenges due to DPC's sparsity and non-uniform structure. Existing methods are limited in capturing sufficient temporal dependencies.…
In this paper, we introduce a Point Recurrent Neural Network (PointRNN) for moving point cloud processing. At each time step, PointRNN takes point coordinates $\boldsymbol{P} \in \mathbb{R}^{n \times 3}$ and point features $\boldsymbol{X}…
LiDAR-based 3D sensors provide point clouds, a canonical 3D representation used in various scene understanding tasks. Modern LiDARs face key challenges in several real-world scenarios, such as long-distance or low-albedo objects, producing…
Point cloud understanding aims to acquire robust and general feature representations from unlabeled data. Masked point modeling-based methods have recently shown significant performance across various downstream tasks. These pre-training…
Point clouds have become an increasingly important representation for 3D medical imaging, offering a compact, surface-preserving alternative to traditional voxel or mesh-based approaches. Recent advances in deep learning have enabled rapid…
In the field of autonomous driving, a variety of sensor data types exist, each representing different modalities of the same scene. Therefore, it is feasible to utilize data from other sensors to facilitate image compression. However, few…
With the overwhelming trend of mask image modeling led by MAE, generative pre-training has shown a remarkable potential to boost the performance of fundamental models in 2D vision. However, in 3D vision, the over-reliance on…
Point cloud completion aims to recover missing geometric structures from incomplete 3D scans, which often suffer from occlusions or limited sensor viewpoints. Existing methods typically assume fixed input/output densities or rely on…
Predicting how the world can evolve in the future is crucial for motion planning in autonomous systems. Classical methods are limited because they rely on costly human annotations in the form of semantic class labels, bounding boxes, and…
Understanding human motion from video is essential for a range of applications, including pose estimation, mesh recovery and action recognition. While state-of-the-art methods predominantly rely on transformer-based architectures, these…
Skeleton-based temporal action segmentation is a fundamental yet challenging task, playing a crucial role in enabling intelligent systems to perceive and respond to human activities. While fully-supervised methods achieve satisfactory…
Recently, immersive media and autonomous driving applications have significantly advanced through 3D Gaussian Splatting (3DGS), which offers high-fidelity rendering and computational efficiency. Despite these advantages, 3DGS as a…
Large and rich data is a prerequisite for effective training of deep neural networks. However, the irregularity of point cloud data makes manual annotation time-consuming and laborious. Self-supervised representation learning, which…
Point tracking models often struggle to generalize to real-world videos because large-scale training data is predominantly synthetic$\unicode{x2014}$the only source currently feasible to produce at scale. Collecting real-world annotations,…
Panoptic tracking enables pixel-level scene interpretation of videos by integrating instance tracking in panoptic segmentation. This provides robots with a spatio-temporal understanding of the environment, an essential attribute for their…