Related papers: MVSBoost: An Efficient Point Cloud-based 3D Recons…
Recently, 3D Gaussian Splatting and its derivatives have achieved significant breakthroughs in large-scale scene reconstruction. However, how to efficiently and stably achieve high-quality geometric fidelity remains a core challenge. To…
As the development of deep neural networks, 3D object recognition is becoming increasingly popular in computer vision community. Many multi-view based methods are proposed to improve the category recognition accuracy. These approaches…
We challenge the common assumption that deeper decoder architectures always yield better performance in point cloud reconstruction. Our analysis reveals that, beyond a certain depth, increasing decoder complexity leads to overfitting and…
We introduce a cutting-edge video compression framework tailored for the age of ubiquitous video data, uniquely designed to serve machine learning applications. Unlike traditional compression methods that prioritize human visual perception,…
Neural implicit surface representation methods have recently shown impressive 3D reconstruction results. However, existing solutions struggle to reconstruct driving scenes due to their large size, highly complex nature and their limited…
Object-centric surface reconstruction from multi-view images is crucial in creating editable digital assets for AR/VR. Due to the lack of geometric constraints, existing methods, e.g., NeuS necessitate annotating the object masks to…
Inferring scene geometry from images via Structure from Motion is a long-standing and fundamental problem in computer vision. While classical approaches and, more recently, depth map predictions only focus on the visible parts of a scene,…
Recently, patch deformation-based methods have demonstrated significant effectiveness in multi-view stereo due to their incorporation of deformable and expandable perception for reconstructing textureless areas. However, these methods…
Deep learning based 3D shape generation methods generally utilize latent features extracted from color images to encode the semantics of objects and guide the shape generation process. These color image semantics only implicitly encode 3D…
Reconstructing detailed 3D scenes from single-view images remains a challenging task due to limitations in existing approaches, which primarily focus on geometric shape recovery, overlooking object appearances and fine shape details. To…
Neural reconstruction models for autonomous driving simulation have made significant strides in recent years, with dynamic models becoming increasingly prevalent. However, these models are typically limited to handling in-domain objects…
Accurate and real-time sensing of targets in three-dimensional (3D) environments is essential for modern machine vision, underpinning emerging technologies such as autonomous systems, robotic manipulation, augmented reality, and intelligent…
Strand-level hair geometry reconstruction is a fundamental problem in virtual human modeling and the digitization of hairstyles. However, existing methods still suffer from a significant trade-off between accuracy and efficiency. Implicit…
A key question in the problem of 3D reconstruction is how to train a machine or a robot to model 3D objects. Many tasks like navigation in real-time systems such as autonomous vehicles directly depend on this problem. These systems usually…
Indoor SLAM often suffers from issues such as scene drifting, double walls, and blind spots, particularly in confined spaces with objects close to the sensors (e.g. LiDAR and cameras) in reconstruction tasks. Real-time visualization of…
Recovering high-quality surfaces from irregular point cloud is ill-posed unless strong geometric priors are available. We introduce an implicit self-prior approach that distills a shape-specific prior directly from the input point cloud…
Explicit surface reconstruction aims to generate a surface mesh that exactly interpolates a given point cloud. This requirement is crucial when the point cloud must lie non-negotiably on the final surface to preserve sharp features and fine…
Recently, methods for neural surface representation and rendering, for example NeuS, have shown that learning neural implicit surfaces through volume rendering is becoming increasingly popular and making good progress. However, these…
3D terrain reconstruction with remote sensing imagery achieves cost-effective and large-scale earth observation and is crucial for safeguarding natural disasters, monitoring ecological changes, and preserving the environment.Recently,…
We introduce MIPS-Fusion, a robust and scalable online RGB-D reconstruction method based on a novel neural implicit representation -- multi-implicit-submap. Different from existing neural RGB-D reconstruction methods lacking either…