Related papers: 4D-StOP: Panoptic Segmentation of 4D LiDAR using S…
Building world models with spatial consistency and real-time interactivity remains a fundamental challenge in computer vision. Current video generation paradigms often struggle with a lack of spatial persistence and insufficient visual…
Despite advances in Multimodal LLMs (MLLMs), their ability to reason over 3D structures and temporal dynamics remains limited, constrained by weak 4D perception and temporal understanding. Existing 3D and 4D Video Question Answering (VQA)…
In this paper, we present ViP-DeepLab, a unified model attempting to tackle the long-standing and challenging inverse projection problem in vision, which we model as restoring the point clouds from perspective image sequences while…
Novel view synthesis has long been a practical but challenging task, although the introduction of numerous methods to solve this problem, even combining advanced representations like 3D Gaussian Splatting, they still struggle to recover…
The 3D LiDAR place recognition aims to estimate a coarse localization in a previously seen environment based on a single scan from a rotating 3D LiDAR sensor. The existing solutions to this problem include hand-crafted point cloud…
Dynamic scene reconstruction is essential in robotic minimally invasive surgery, providing crucial spatial information that enhances surgical precision and outcomes. However, existing methods struggle to address the complex, temporally…
Generating high-quality 3D assets from textual descriptions remains a pivotal challenge in computer graphics and vision research. Due to the scarcity of 3D data, state-of-the-art approaches utilize pre-trained 2D diffusion priors, optimized…
Learning from Demonstration (LfD) has emerged as a crucial method for robots to acquire new skills. However, when given suboptimal task trajectory demonstrations with shape characteristics reflecting human preferences but subpar dynamic…
Weakly supervised object detection (WSOD), which is an effective way to train an object detection model using only image-level annotations, has attracted considerable attention from researchers. However, most of the existing methods, which…
LiDAR point cloud semantic segmentation is essential for interpreting 3D environments in applications such as autonomous driving and robotics. Recent methods achieve strong performance by exploiting different point cloud representations or…
In this paper we introduce a Transformer-based approach to video object segmentation (VOS). To address compounding error and scalability issues of prior work, we propose a scalable, end-to-end method for VOS called Sparse Spatiotemporal…
Recent advances in 2D/3D generative models enable the generation of dynamic 3D objects from a single-view video. Existing approaches utilize score distillation sampling to form the dynamic scene as dynamic NeRF or dense 3D Gaussians.…
Safe navigation with simultaneous localization and mapping (SLAM) for autonomous robots is crucial in challenging environments. To achieve this goal, detecting moving objects in the surroundings and building a static map are essential.…
4D LiDAR semantic segmentation, also referred to as multi-scan semantic segmentation, plays a crucial role in enhancing the environmental understanding capabilities of autonomous vehicles or robots. It classifies the semantic category of…
Dynamic mode decomposition (DMD) provides a regression framework for adaptively learning a best-fit linear dynamics model over snapshots of temporal, or spatio-temporal, data. A diversity of regression techniques have been developed for…
4D radar measurements offer an affordable and weather-robust solution for 3D perception. However, the inherent sparsity and noise of radar point clouds present significant challenges for accurate 3D object detection, underscoring the need…
Distribution Matching Distillation (DMD) distills score-based generative models into efficient one-step generators, without requiring a one-to-one correspondence with the sampling trajectories of their teachers. Yet, the limited capacity of…
Visual place recognition methods struggle with occlusions and partial visual overlaps. We propose a novel visual place recognition approach based on overlap prediction, called VOP, shifting from traditional reliance on global image…
LiDAR point cloud analysis is a core task for 3D computer vision, especially for autonomous driving. However, due to the severe sparsity and noise interference in the single sweep LiDAR point cloud, the accurate semantic segmentation is…
As camera and LiDAR sensors capture complementary information used in autonomous driving, great efforts have been made to develop semantic segmentation algorithms through multi-modality data fusion. However, fusion-based approaches require…