Related papers: FUSE-Flow: Scalable Real-Time Multi-View Point Clo…
Deep learning-based image enhancement methods face a fundamental trade-off between computational efficiency and representational capacity. For example, although a conventional three-dimensional Look-Up Table (3D LUT) can process a degraded…
We propose POse-guided SElective Fusion (POSEFusion), a single-view human volumetric capture method that leverages tracking-based methods and tracking-free inference to achieve high-fidelity and dynamic 3D reconstruction. By contributing a…
3D point clouds are rich in geometric structure information, while 2D images contain important and continuous texture information. Combining 2D information to achieve better 3D semantic segmentation has become mainstream in 3D scene…
Recently, learning multi-view neural surface reconstruction with the supervision of point clouds or depth maps has been a promising way. However, due to the underutilization of prior information, current methods still struggle with the…
3D surface reconstruction from point clouds is a key step in areas such as content creation, archaeology, digital cultural heritage, and engineering. Current approaches either try to optimize a non-data-driven surface representation to fit…
Computational Fluid Dynamics (CFD) serves as a powerful tool for simulating fluid flow across diverse industries. High-resolution CFD simulations offer valuable insights into fluid behavior and flow patterns, aiding in optimizing design…
Cross-modal 3D retrieval is a critical yet challenging task, aiming to achieve bi-directional retrieval between 3D and text modalities. Current methods predominantly rely on a certain 3D representation (e.g., point cloud), with few…
3D scene reconstruction under unposed sparse viewpoints is a highly challenging yet practically important problem, especially in outdoor scenes due to complex lighting and scale variation. With extremely limited input views, directly…
The recent advances in 3D sensing technology have made possible the capture of point clouds in significantly high resolution. However, increased detail usually comes at the expense of high storage, as well as computational costs in terms of…
Multi-beam LiDAR sensors, as used on autonomous vehicles and mobile robots, acquire sequences of 3D range scans ("frames"). Each frame covers the scene sparsely, due to limited angular scanning resolution and occlusion. The sparsity…
Recently, neural network for scene flow estimation show impressive results on automotive data such as the KITTI benchmark. However, despite of using sophisticated rigidity assumptions and parametrizations, such networks are typically…
Recent advancements in sensor technology and deep learning have led to significant progress in 3D human body reconstruction. However, most existing approaches rely on data from a specific sensor, which can be unreliable due to the inherent…
Given the rapid development of 3D scanners, point clouds are becoming popular in AI-driven machines. However, point cloud data is inherently sparse and irregular, causing significant difficulties for machine perception. In this work, we…
We present PointFusion, a generic 3D object detection method that leverages both image and 3D point cloud information. Unlike existing methods that either use multi-stage pipelines or hold sensor and dataset-specific assumptions,…
We present FlowCapX, a physics-enhanced framework for flow reconstruction from sparse video inputs, addressing the challenge of jointly optimizing complex physical constraints and sparse observational data over long time horizons. Existing…
Recently normalizing flows (NFs) have demonstrated state-of-the-art performance on modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time. However, these flow-based models still require long training…
Many recent works on 3D object detection have focused on designing neural network architectures that can consume point cloud data. While these approaches demonstrate encouraging performance, they are typically based on a single modality and…
Text-based generation and editing of 3D scenes hold significant potential for streamlining content creation through intuitive user interactions. While recent advances leverage 3D Gaussian Splatting (3DGS) for high-fidelity and real-time…
Recovering the 3D representation of an object from single-view or multi-view RGB images by deep neural networks has attracted increasing attention in the past few years. Several mainstream works (e.g., 3D-R2N2) use recurrent neural networks…
3D object detection with multi-sensors is essential for an accurate and reliable perception system of autonomous driving and robotics. Existing 3D detectors significantly improve the accuracy by adopting a two-stage paradigm which merely…