Search Results for author:
Found 36 papers, 12 papers with code
A Comprehensive Survey and Taxonomy on Point Cloud Registration Based on Deep Learning
Point cloud registration (PCR) involves determining a rigid transformation that aligns one point cloud to another.
Delving into the Trajectory Long-tail Distribution for Muti-object Tracking
In this study, we pioneer an exploration into the distribution patterns of tracking data and identify a pronounced long-tail distribution issue within existing MOT datasets.
PSDF: Prior-Driven Neural Implicit Surface Learning for Multi-view Reconstruction
While NISR has shown impressive results on simple scenes, it remains challenging to recover delicate geometry from uncontrolled real-world scenes which is caused by its underconstrained optimization.
PR-NeuS: A Prior-based Residual Learning Paradigm for Fast Multi-view Neural Surface Reconstruction
In this work, we propose a prior-based residual learning paradigm for fast multi-view neural surface reconstruction.
DiffusionPCR: Diffusion Models for Robust Multi-Step Point Cloud Registration
We propose formulating PCR as a denoising diffusion probabilistic process, mapping noisy transformations to the ground truth.
Merlin:Empowering Multimodal LLMs with Foresight Minds
Then, FIT requires MLLMs to first predict trajectories of related objects and then reason about potential future events based on them.
Ranked #61 on
Visual Question Answering
on MM-Vet
PG-NeuS: Robust and Efficient Point Guidance for Multi-View Neural Surface Reconstruction
Recently, learning multi-view neural surface reconstruction with the supervision of point clouds or depth maps has been a promising way.
MOTRv3: Release-Fetch Supervision for End-to-End Multi-Object Tracking
Although end-to-end multi-object trackers like MOTR enjoy the merits of simplicity, they suffer from the conflict between detection and association seriously, resulting in unsatisfactory convergence dynamics.
Deep Seam Prediction for Image Stitching Based on Selection Consistency Loss
To our knowledge, the proposed DSeam is the first deep learning based seam prediction method for image stitching.
DMNet: Delaunay Meshing Network for 3D Shape Representation
We model the Delaunay triangulation as a dual graph, extract local geometric information from the points, and embed it into the structural representation of Delaunay triangulation in an organic way, benefiting fine-grained details reconstruction.
Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representation
VLM joints the information in the generated visual prompts and the textual prompts from a pre-defined Trackbook to obtain instance-level pseudo textual description, which is domain invariant to different tracking scenes.
Quality Matters: Embracing Quality Clues for Robust 3D Multi-Object Tracking
Recent advanced works generally employ a series of object attributes, e. g., position, size, velocity, and appearance, to provide the clues for the association in 3D MOT.
Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction
Recently, neural implicit surfaces learning by volume rendering has become popular for multi-view reconstruction.
SC^2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration
In this paper, we present a second order spatial compatibility (SC^2) measure based method for efficient and robust point cloud registration (PCR), called SC^2-PCR.
SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration
In this paper, we present a second order spatial compatibility (SC^2) measure based method for efficient and robust point cloud registration (PCR), called SC^2-PCR.
Ranked #1 on
Point Cloud Registration
on FP-O-H
DetarNet: Decoupling Translation and Rotation by Siamese Network for Point Cloud Registration
In this paper, we propose a neural network named DetarNet to decouple the translation $t$ and rotation $R$, so as to overcome the performance degradation due to their mutual interference in point cloud registration.
Non-local Recurrent Regularization Networks for Multi-view Stereo
However, existing recurrent methods only model the local dependencies in the depth domain, which greatly limits the capability of capturing the global scene context along the depth dimension.
LIF-Seg: LiDAR and Camera Image Fusion for 3D LiDAR Semantic Segmentation
However, two major issues of the fusion between camera and LiDAR hinder its performance, \ie, how to effectively fuse these two modalities and how to precisely align them (suffering from the weak spatiotemporal synchronization problem).
Cascade Network with Guided Loss and Hybrid Attention for Finding Good Correspondences
We then propose a hybrid attention block to extract feature, which integrates the Bayesian attentive context normalization (BACN) and channel-wise attention (CA).
DeepDT: Learning Geometry From Delaunay Triangulation for Surface Reconstruction
DeepDT learns to predict inside/outside labels of Delaunay tetrahedrons directly from a point cloud and corresponding Delaunay triangulation.
PVSNet: Pixelwise Visibility-Aware Multi-View Stereo Network
We present a pixelwise visibility network to learn the visibility information for different neighboring images before computing the multi-view similarity, and then construct an adaptive weighted cost volume with the visibility information.
Cascade Network with Guided Loss and Hybrid Attention for Two-view Geometry
We then propose a hybrid attention block to extract feature, which integrates the bayesian attentive context normalization (BACN) and channel-wise attention (CA).
Planar Prior Assisted PatchMatch Multi-View Stereo
In detail, we utilize a probabilistic graphical model to embed planar models into PatchMatch multi-view stereo and contribute a novel multi-view aggregated matching cost.
Learning Inverse Depth Regression for Multi-View Stereo with Correlation Cost Volume
This can be attributed to the memory-consuming cost volume representation and inappropriate depth inference.
JSNet: Joint Instance and Semantic Segmentation of 3D Point Clouds
In this paper, we propose a novel joint instance and semantic segmentation approach, which is called JSNet, in order to address the instance and semantic segmentation of 3D point clouds simultaneously.
Ranked #2 on
Semantic Segmentation
on ShapeNet
IoU-uniform R-CNN: Breaking Through the Limitations of RPN
Region Proposal Network (RPN) is the cornerstone of two-stage object detectors, it generates a sparse set of object proposals and alleviates the extrem foregroundbackground class imbalance problem during training.
SSRNet: Scalable 3D Surface Reconstruction Network
Existing learning-based surface reconstruction methods from point clouds are still facing challenges in terms of scalability and preservation of details on large-scale point clouds.
Localization-aware Channel Pruning for Object Detection
In this paper, based on discrimination-aware channel pruning (DCP) which is state-of-the-art pruning method for classification, we propose a localization-aware auxiliary network to find out the channels with key information for classification and regression so that we can conduct channel pruning directly for object detection, which saves lots of time and computing resources.
GLA-Net: An Attention Network with Guided Loss for Mismatch Removal
To establish the link between Fn-score and loss, we propose to guide the loss with the Fn-score directly.
Multi-Scale Geometric Consistency Guided Multi-View Stereo
For the depth estimation of low-textured areas, we further propose to combine ACMH with multi-scale geometric consistency guidance (ACMM) to obtain the reliable depth estimates for low-textured areas at coarser scales and guarantee that they can be propagated to finer scales.
Ranked #9 on
Point Clouds
on Tanks and Temples
GPU Accelerated Cascade Hashing Image Matching for Large Scale 3D Reconstruction
In this paper, we proposed a GPU accelerated image matching method with improved Cascade Hashing.
Multi-View Stereo with Asymmetric Checkerboard Propagation and Multi-Hypothesis Joint View Selection
In computer vision domain, how to fast and accurately perform multiview stereo (MVS) is still a challenging problem.
Trilaminar Multiway Reconstruction Tree for Efficient Large Scale Structure from Motion
Accuracy and efficiency are two key problems in large scale incremental Structure from Motion (SfM).
Convolutional Regression for Visual Tracking
In this paper, we propose a Convolutional Regression framework for visual tracking (CRT).
Once for All: a Two-flow Convolutional Neural Network for Visual Tracking
As a result, the model need to be initialized and retrained for different objects.
Asymmetrical Gauss Mixture Models for Point Sets Matching
The probabilistic methods based on Symmetrical Gauss Mixture Model (SGMM) have achieved great success in point sets registration, but are seldom used to find the correspondences between two images due to the complexity of the non-rigid transformation and too many outliers.
