Search Results for author:
Found 20 papers, 6 papers with code
HybridTrack: A Hybrid Approach for Robust Multi-Object Tracking
The evolution of Advanced Driver Assistance Systems (ADAS) has increased the need for robust and generalizable algorithms for multi-object tracking.
Strada-LLM: Graph LLM for traffic prediction
Furthermore, we adopt a lightweight approach for efficient domain adaptation when facing new data distributions in few-shot fashion.
ProtoSeg: A Prototype-Based Point Cloud Instance Segmentation Method
This paper presents a novel neural network architecture for performing instance segmentation on 3D point clouds.
RESSCAL3D++: Joint Acquisition and Semantic Segmentation of 3D Point Clouds
While existing approaches typically separate acquisition and processing for each frame, the advent of resolution-scalable 3D sensors offers an opportunity to overcome this paradigm and fully leverage the otherwise wasted acquisition time to initiate processing.
GINTRIP: Interpretable Temporal Graph Regression using Information bottleneck and Prototype-based method
While interpretability concerns in Graph Neural Networks (GNNs) mirror those of DNNs, to the best of our knowledge, no notable work has addressed the interpretability of temporal GNNs using a combination of Information Bottleneck (IB) principles and prototype-based methods.
Efficient and Scalable Point Cloud Generation with Sparse Point-Voxel Diffusion Models
Our fastest variant outperforms all non-diffusion generative approaches on unconditional shape generation, the most popular benchmark for evaluating point cloud generative models, while our largest model achieves state-of-the-art results among diffusion methods, with a runtime approximately 70% of the previously state-of-the-art PVD.
LAM3D: Leveraging Attention for Monocular 3D Object Detection
Since the introduction of the self-attention mechanism and the adoption of the Transformer architecture for Computer Vision tasks, the Vision Transformer-based architectures gained a lot of popularity in the field, being used for tasks such as image classification, object detection and image segmentation.
Joint prototype and coefficient prediction for 3D instance segmentation
Notably, with only 0. 8% of the total inference time, our method exhibits an over 20-fold reduction in the variance of inference time compared to existing methods.
Improved Block Merging for 3D Point Cloud Instance Segmentation
This paper proposes a novel block merging algorithm suitable for any block-based 3D instance segmentation technique.
RT-GS2: Real-Time Generalizable Semantic Segmentation for 3D Gaussian Representations of Radiance Fields
Our method adopts a new approach by first extracting view-independent 3D Gaussian features in a self-supervised manner, followed by a novel View-Dependent / View-Independent (VDVI) feature fusion to enhance semantic consistency over different views.
DeepKalPose: An Enhanced Deep-Learning Kalman Filter for Temporally Consistent Monocular Vehicle Pose Estimation
This paper presents DeepKalPose, a novel approach for enhancing temporal consistency in monocular vehicle pose estimation applied on video through a deep-learning-based Kalman Filter.
RESSCAL3D: Resolution Scalable 3D Semantic Segmentation of Point Clouds
To the best of our knowledge, the proposed method is the first to propose a resolution-scalable approach for 3D semantic segmentation of point clouds based on deep learning.
ExpPoint-MAE: Better interpretability and performance for self-supervised point cloud transformers
In this paper we delve into the properties of transformers, attained through self-supervision, in the point cloud domain.
Ranked #16 on
3D Point Cloud Classification
on ModelNet40
(using extra training data)
3D Point Cloud Classification
Explainable artificial intelligence
3DBodyNet: Fast Reconstruction of 3D Animatable Human Body Shape from a Single Commodity Depth Camera
As easy-to-use as taking a photo using a mobile phone, our algorithm only needs two depth images of the front-facing and back-facing bodies.
Method for Registration of 3D Shapes Without Overlap for Known 3D Priors
In this letter, to the best of knowledge, the first method for the registration of 3D shapes without overlap, assuming that the shapes correspond to partial views of a known semi-rigid 3D prior is presented.
MaskLayer: Enabling scalable deep learning solutions by training embedded feature sets
To the best of our knowledge, this is the first work presenting a generic solution able to achieve quality scalable results within the deep learning framework.
Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
Among the existing GCNNs, many methods can be viewed as instances of a neural message passing motif; features of nodes are passed around their neighbors, aggregated and transformed to produce better nodes' representations.
Learning to Estimate the Body Shape Under Clothing from a Single 3D Scan
In this paper, we propose the first learning-based approach to estimate the human body shape under clothing from a single dressed-human scan, dubbed Body PointNet.
Multi-modal deep network for RGB-D segmentation of clothes
In this Letter, the authors propose a deep learning based method to perform semantic segmentation of clothes from RGB-D images of people.
A generic method of wearable items virtual try-on
In this paper, we present the first general method for virtual try-ons that is fully automatic and suitable for many items including garments, hair, shoes, watches, necklaces, hats, and so on.
