Search Results for author:
Found 37 papers, 19 papers with code
3D Part Segmentation via Geometric Aggregation of 2D Visual Features
Supervised 3D part segmentation models are tailored for a fixed set of objects and parts, limiting their transferability to open-set, real-world scenarios.
PerLA: Perceptive 3D Language Assistant
Enabling Large Language Models (LLMs) to understand the 3D physical world is an emerging yet challenging research direction.
Functionality understanding and segmentation in 3D scenes
Fun3DU uses a language model to parse the task description through Chain-of-Thought reasoning in order to identify the object of interest.
Exploring Fine-grained Retail Product Discrimination with Zero-shot Object Classification Using Vision-Language Models
Secondly, we benchmark the zero-shot object classification performance of state-of-the-art vision-language models (VLMs) on the proposed MIMEX dataset.
Vocabulary-Free 3D Instance Segmentation with Vision and Language Assistant
We evaluate our method using ScanNet200 and Replica, outperforming existing methods in both vocabulary-free and open-vocabulary settings.
6DGS: 6D Pose Estimation from a Single Image and a 3D Gaussian Splatting Model
Each Ellicell ray is associated with the rendering parameters of each ellipsoid, which in turn is used to obtain the best bindings between the target image pixels and the cast rays.
High-resolution open-vocabulary object 6D pose estimation
We use the textual prompt to identify the unseen object in the scenes and then obtain high-resolution multi-scale features.
Wild Berry image dataset collected in Finnish forests and peatlands using drones
Berry picking has long-standing traditions in Finland, yet it is challenging and can potentially be dangerous.
Light-weight Retinal Layer Segmentation with Global Reasoning
Automatic retinal layer segmentation with medical images, such as optical coherence tomography (OCT) images, serves as an important tool for diagnosing ophthalmic diseases.
IFFNeRF: Initialisation Free and Fast 6DoF pose estimation from a single image and a NeRF model
We introduce IFFNeRF to estimate the six degrees-of-freedom (6DoF) camera pose of a given image, building on the Neural Radiance Fields (NeRF) formulation.
Novel class discovery meets foundation models for 3D semantic segmentation
Firstly, it introduces the novel task of NCD for point cloud semantic segmentation.
ZeroReg: Zero-Shot Point Cloud Registration with Foundation Models
To address this, we construct scene graphs to capture spatial relationships among objects and apply a graph matching algorithm to these graphs to accurately identify matched objects.
Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding
Zero-shot 3D point cloud understanding can be achieved via 2D Vision-Language Models (VLMs).
Open-vocabulary object 6D pose estimation
We introduce the new setting of open-vocabulary object 6D pose estimation, in which a textual prompt is used to specify the object of interest.
FreeZe: Training-free zero-shot 6D pose estimation with geometric and vision foundation models
We also introduce a novel algorithm to solve ambiguous cases due to geometrically symmetric objects that is based on visual features.
Delving into CLIP latent space for Video Anomaly Recognition
We tackle the complex problem of detecting and recognising anomalies in surveillance videos at the frame level, utilising only video-level supervision.
Detect, Augment, Compose, and Adapt: Four Steps for Unsupervised Domain Adaptation in Object Detection
Unsupervised domain adaptation (UDA) plays a crucial role in object detection when adapting a source-trained detector to a target domain without annotated data.
Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation
In this study, we introduce compositional semantic mixing for point cloud domain adaptation, representing the first unsupervised domain adaptation technique for point cloud segmentation based on semantic and geometric sample mixing.
Survey on video anomaly detection in dynamic scenes with moving cameras
The increasing popularity of compact and inexpensive cameras, e. g.~dash cameras, body cameras, and cameras equipped on robots, has sparked a growing interest in detecting anomalies within dynamic scenes recorded by moving cameras.
Attentive Multimodal Fusion for Optical and Scene Flow
This paper presents an investigation into the estimation of optical and scene flow using RGBD information in scenarios where the RGB modality is affected by noise or captured in dark environments.
Revisiting Fully Convolutional Geometric Features for Object 6D Pose Estimation
Recent works on 6D object pose estimation focus on learning keypoint correspondences between images and object models, and then determine the object pose through RANSAC-based algorithms or by directly regressing the pose with end-to-end optimisations.
PatchMixer: Rethinking network design to boost generalization for 3D point cloud understanding
The recent trend in deep learning methods for 3D point cloud understanding is to propose increasingly sophisticated architectures either to better capture 3D geometries or by introducing possibly undesired inductive biases.
The MONET dataset: Multimodal drone thermal dataset recorded in rural scenarios
MONET is different from previous thermal drone datasets because it features multimodal data, including rural scenes captured with thermal cameras containing both person and vehicle targets, along with trajectory information and metadata.
Novel Class Discovery for 3D Point Cloud Semantic Segmentation
Firstly, we address the new problem of NCD for point cloud semantic segmentation.
Detection-aware multi-object tracking evaluation
How would you fairly evaluate two multi-object tracking algorithms (i. e. trackers), each one employing a different object detector?
1st Workshop on Maritime Computer Vision (MaCVi) 2023: Challenge Results
The 1$^{\text{st}}$ Workshop on Maritime Computer Vision (MaCVi) 2023 focused on maritime computer vision for Unmanned Aerial Vehicles (UAV) and Unmanned Surface Vehicle (USV), and organized several subchallenges in this domain: (i) UAV-based Maritime Object Detection, (ii) UAV-based Maritime Object Tracking, (iii) USV-based Maritime Obstacle Segmentation and (iv) USV-based Maritime Obstacle Detection.
Overlap-guided Gaussian Mixture Models for Point Cloud Registration
Probabilistic 3D point cloud registration methods have shown competitive performance in overcoming noise, outliers, and density variations.
VM-NeRF: Tackling Sparsity in NeRF with View Morphing
A well-known limitation of NeRF methods is their reliance on data: the fewer the viewpoints, the higher the likelihood of overfitting.
Data Augmentation-free Unsupervised Learning for 3D Point Cloud Understanding
Unsupervised learning on 3D point clouds has undergone a rapid evolution, especially thanks to data augmentation-based contrastive methods.
GIPSO: Geometrically Informed Propagation for Online Adaptation in 3D LiDAR Segmentation
Our experiments show the effectiveness of our segmentation approach on thousands of real-world point clouds.
CoSMix: Compositional Semantic Mix for Domain Adaptation in 3D LiDAR Segmentation
We propose a new approach of sample mixing for point cloud UDA, namely Compositional Semantic Mix (CoSMix), the first UDA approach for point cloud segmentation based on sample mixing.
Loop closure detection using local 3D deep descriptors
We compare our L3D-based loop closure approach with recent approaches on LiDAR data and achieve state-of-the-art loop closure detection accuracy.
Learning general and distinctive 3D local deep descriptors for point cloud registration
An effective 3D descriptor should be invariant to different geometric transformations, such as scale and rotation, robust to occlusions and clutter, and capable of generalising to different application domains.
Ranked #1 on
Point Cloud Registration
on ETH (trained on 3DMatch)
Distinctive 3D local deep descriptors
We present a simple but yet effective method for learning distinctive 3D local deep descriptors (DIPs) that can be used to register point clouds without requiring an initial alignment.
Ranked #2 on
Point Cloud Registration
on ETH (trained on 3DMatch)
Novel-View Human Action Synthesis
We first estimate the 3D mesh of the target body and transfer the rough textures from the 2D images to the mesh.
Multi-view data capture using edge-synchronised mobiles
We have designed an edge computing unit that supervises the relaying of timing triggers to and from multiple mobiles, in addition to synchronising frame harvesting.
3D Shape Segmentation with Geometric Deep Learning
The semantic segmentation of 3D shapes with a high-density of vertices could be impractical due to large memory requirements.
