Related papers: Unsupervised Learning of 3D Scene Flow with 3D Odo…

Open-world 3D scene understanding is a critical challenge that involves recognizing and distinguishing diverse objects and categories from 3D data, such as point clouds, without relying on manual annotations. Traditional methods struggle…

Scene flow estimation is the task of describing the 3D motion field between temporally successive point clouds. State-of-the-art methods use strong priors and test-time optimization techniques, but require on the order of tens of seconds to…

Unsupervised learning of optical flow, which leverages the supervision from view synthesis, has emerged as a promising alternative to supervised methods. However, the objective of unsupervised learning is likely to be unreliable in…

Occupancy prediction reconstructs 3D structures of surrounding environments. It provides detailed information for autonomous driving planning and navigation. However, most existing methods heavily rely on the LiDAR point clouds to generate…

Event cameras such as DAVIS can simultaneously output high temporal resolution events and low frame-rate intensity images, which own great potential in capturing scene motion, such as optical flow estimation. Most of the existing optical…

Scene flow estimation, which aims to predict per-point 3D displacements of dynamic scenes, is a fundamental task in the computer vision field. However, previous works commonly suffer from unreliable correlation caused by locally constrained…

Odometry is a critical task for autonomous systems for self-localization and navigation. We propose a novel LiDAR-Visual odometry framework that integrates LiDAR point clouds and images for accurate and robust pose estimation. Our method…

Learning robust visuomotor policies that generalize across diverse objects and interaction dynamics remains a central challenge in robotic manipulation. Most existing approaches rely on direct observation-to-action mappings or compress…

Processing point clouds using deep neural networks is still a challenging task. Most existing models focus on object detection and registration with deep neural networks using point clouds. In this paper, we propose a deep model that learns…

Existing optical flow methods are erroneous in challenging scenes, such as fog, rain, and night because the basic optical flow assumptions such as brightness and gradient constancy are broken. To address this problem, we present an…

Performing facial expression transfer under one-shot setting has been increasing in popularity among research community with a focus on precise control of expressions. Existing techniques showcase compelling results in perceiving…

We propose a novel method for learning convolutional neural image representations without manual supervision. We use motion cues in the form of optical flow, to supervise representations of static images. The obvious approach of training a…

We present Seen2Scene, the first flow matching-based approach that trains directly on incomplete, real-world 3D scans for scene completion and generation. Unlike prior methods that rely on complete and hence synthetic 3D data, our approach…

We study the problem of estimating optical flow from event cameras. One important issue is how to build a high-quality event-flow dataset with accurate event values and flow labels. Previous datasets are created by either capturing real…

Most recent 6D object pose methods use 2D optical flow to refine their results. However, the general optical flow methods typically do not consider the target's 3D shape information during matching, making them less effective in 6D object…

Optical flow estimation is crucial for various applications in vision and robotics. As the difficulty of collecting ground truth optical flow in real-world scenarios, most of the existing methods of learning optical flow still adopt…

In crowded urban environments where traffic is dense, current technologies struggle to oversee tight navigation, but surface-level understanding allows autonomous vehicles to safely assess proximity to surrounding obstacles. 3D or 2D scene…

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…

Occlusions hinder point cloud frame alignment in LiDAR data, a challenge inadequately addressed by scene flow models tested mainly on occlusion-free datasets. Attempts to integrate occlusion handling within networks often suffer accuracy…

Unsupervised 3D representation learning reduces the burden of labeling multimodal 3D data for fusion perception tasks. Among different pre-training paradigms, differentiable-rendering-based methods have shown most promise. However, existing…