Related papers: Inferring Neural Signed Distance Functions by Over…

Neural Scene Flow Prior (NSFP) is of significant interest to the vision community due to its inherent robustness to out-of-distribution (OOD) effects and its ability to deal with dense lidar points. The approach utilizes a coordinate neural…

Existing learning-based point feature descriptors are usually task-agnostic, which pursue describing the individual 3D point clouds as accurate as possible. However, the matching task aims at describing the corresponding points consistently…

Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is especially important for semantic segmentation tasks involving 3D datasets that are often significantly…

Recovering CAD models from point clouds requires reconstructing their topology and sketch-based extrusion primitives. A dominant paradigm for representing sketches involves implicit neural representations such as Signed Distance Fields…

In point clouds, noise directly perturbs point coordinates that encode both spatial location and geometry, making one-to-one correspondence construction more challenging than in images. Existing methods impose statistical mappings across…

Normal estimation for unstructured point clouds is an important task in 3D computer vision. Current methods achieve encouraging results by mapping local patches to normal vectors or learning local surface fitting using neural networks.…

Existing fine-tuning methods either tune all parameters of the pre-trained model (full fine-tuning), which is not efficient, or only tune the last linear layer (linear probing), which suffers a significant accuracy drop compared to the full…

3D point cloud semantic segmentation is a challenging topic in the computer vision field. Most of the existing methods in literature require a large amount of fully labeled training data, but it is extremely time-consuming to obtain these…

Pretraining on large labeled datasets is a prerequisite to achieve good performance in many computer vision tasks like 2D object recognition, video classification etc. However, pretraining is not widely used for 3D recognition tasks where…

We propose a novel method for reconstructing explicit parameterized surfaces from Signed Distance Fields (SDFs), a widely used implicit neural representation (INR) for 3D surfaces. While traditional reconstruction methods like Marching…

3D point cloud analysis has drawn a lot of research attention due to its wide applications. However, collecting massive labelled 3D point cloud data is both time-consuming and labor-intensive. This calls for data-efficient learning methods.…

Feature point detection and description is the backbone for various computer vision applications, such as Structure-from-Motion, visual SLAM, and visual place recognition. While learning-based methods have surpassed traditional handcrafted…

Assisted by the availability of data and high performance computing, deep learning techniques have achieved breakthroughs and surpassed human performance empirically in difficult tasks, including object recognition, speech recognition, and…

Safety of the Intended Functionality (SOTIF) addresses sensor performance limitations and deep learning-based object detection insufficiencies to ensure the intended functionality of Automated Driving Systems (ADS). This paper presents a…

Signed Distance Function (SDF)-based volume rendering has demonstrated significant capabilities in surface reconstruction. Although promising, SDF-based methods often fail to capture detailed geometric structures, resulting in visible…

We present a novel online depth map fusion approach that learns depth map aggregation in a latent feature space. While previous fusion methods use an explicit scene representation like signed distance functions (SDFs), we propose a learned…

A key step in any scanning-based asset creation workflow is to convert unordered point clouds to a surface. Classical methods (e.g., Poisson reconstruction) start to degrade in the presence of noisy and partial scans. Hence, deep learning…

Recovery of a 3D head model including the complete face and hair regions is still a challenging problem in computer vision and graphics. In this paper, we consider this problem using only a few multi-view portrait images as input. Previous…

Neural surface reconstruction relies heavily on accurate camera poses as input. Despite utilizing advanced pose estimators like COLMAP or ARKit, camera poses can still be noisy. Existing pose-NeRF joint optimization methods handle poses…

With the rapid progress of multimodal foundation models and predictive pre-training, an important open question is how to equip 3D point clouds with a pre-training paradigm that is better aligned with next-token and next-embedding learning.…