224 citations · 429 across the 42 of their papers we have counts for
28 papers · 1 filter
CAIRN: Cross-Room 3D Scene Understanding with Topology-Aware Large Multimodal Models
He Liang, Chenyang Ma, Yiming Zhang +4
Existing 3D scene-grounded Large Language Models (3D-LLMs) focus on answering questions grounded in simplified single-room 3D scenes, lacking the ability to reason over real-world…
Data Factory with Minimal Human Effort Using VLMs
Jiaojiao Ye, Jiaxing Zhong, Qian Xie +3
Generating enough and diverse data through augmentation offers an efficient solution to the time-consuming and labour-intensive process of collecting and annotating pixel-wise imag…
Towards Multi-Modal Animal Pose Estimation: A Survey and In-Depth Analysis
Qianyi Deng, Oishi Deb, Amir Patel +4
Animal pose estimation (APE) aims to locate the animal body parts using a diverse array of sensor and modality inputs (e.g. RGB cameras, LiDAR, infrared, IMU, acoustic and language…
MambaLoc: Efficient Camera Localisation via State Space Model
Jialu Wang, Kaichen Zhou, Andrew Markham +1
Location information is pivotal for the automation and intelligence of terminal devices and edge-cloud IoT systems, such as autonomous vehicles and augmented reality. However, achi…
Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Models
Madhu Vankadari, Samuel Hodgson, Sangyun Shin +2
Self-supervised depth estimation algorithms rely heavily on frame-warping relationships, exhibiting substantial performance degradation when applied in challenging circumstances, s…
ZeST: Zero-Shot Material Transfer from a Single Image
Ta-Ying Cheng, Prafull Sharma, Andrew Markham +2
We propose ZeST, a method for zero-shot material transfer to an object in the input image given a material exemplar image. ZeST leverages existing diffusion adapters to extract imp…
WSCLoc: Weakly-Supervised Sparse-View Camera Relocalization
Jialu Wang, Kaichen Zhou, Andrew Markham +1
Despite the advancements in deep learning for camera relocalization tasks, obtaining ground truth pose labels required for the training process remains a costly endeavor. While cur…
SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors
Chenyang Ma, Kai Lu, Ta-Ying Cheng +2
Current state-of-the-art spatial reasoning-enhanced VLMs are trained to excel at spatial visual question answering (VQA). However, we believe that higher-level 3D-aware tasks, such…
Gen4Gen: Generative Data Pipeline for Generative Multi-Concept Composition
Chun-Hsiao Yeh, Ta-Ying Cheng, He-Yen Hsieh +6
Recent text-to-image diffusion models are able to learn and synthesize images containing novel, personalized concepts (e.g., their own pets or specific items) with just a few examp…
Learning Continuous 3D Words for Text-to-Image Generation
Ta-Ying Cheng, Matheus Gadelha, Thibault Groueix +4
Current controls over diffusion models (e.g., through text or ControlNet) for image generation fall short in recognizing abstract, continuous attributes like illumination direction…
Manydepth2: Motion-Aware Self-Supervised Monocular Depth Estimation in Dynamic Scenes
Kaichen Zhou, Jia-Wang Bian, Jian-Qing Zheng +4
Despite advancements in self-supervised monocular depth estimation, challenges persist in dynamic scenarios due to the dependence on assumptions about a static world. In this paper…
Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation
Sangyun Shin, Kaichen Zhou, Madhu Vankadari +2
Coarse-to-fine 3D instance segmentation methods show weak performances compared to recent Grouping-based, Kernel-based and Transformer-based methods. We argue that this is due to t…
3DMiner: Discovering Shapes from Large-Scale Unannotated Image Datasets
Ta-Ying Cheng, Matheus Gadelha, Soren Pirk +4
We present 3DMiner -- a pipeline for mining 3D shapes from challenging large-scale unannotated image datasets. Unlike other unsupervised 3D reconstruction methods, we assume that,…
Deep Learning for Visual Localization and Mapping: A Survey
Changhao Chen, Bing Wang, Chris Xiaoxuan Lu +2
Deep learning based localization and mapping approaches have recently emerged as a new research direction and receive significant attentions from both industry and academia. Instea…
Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation
Jia-Xing Zhong, Ta-Ying Cheng, Yuhang He +4
A truly generalizable approach to rigid segmentation and motion estimation is fundamental to 3D understanding of articulated objects and moving scenes. In view of the closely inter…
Sample, Crop, Track: Self-Supervised Mobile 3D Object Detection for Urban Driving LiDAR
Sangyun Shin, Stuart Golodetz, Madhu Vankadari +3
Deep learning has led to great progress in the detection of mobile (i.e. movement-capable) objects in urban driving scenes in recent years. Supervised approaches typically require…
Meta-Sampler: Almost-Universal yet Task-Oriented Sampling for Point Clouds
Ta-Ying Cheng, Qingyong Hu, Qian Xie +2
Sampling is a key operation in point-cloud task and acts to increase computational efficiency and tractability by discarding redundant points. Universal sampling algorithms (e.g.,…
No Pain, Big Gain: Classify Dynamic Point Cloud Sequences with Static Models by Fitting Feature-level Space-time Surfaces
Jia-Xing Zhong, Kaichen Zhou, Qingyong Hu +3
Scene flow is a powerful tool for capturing the motion field of 3D point clouds. However, it is difficult to directly apply flow-based models to dynamic point cloud classification…
Real-Time Hybrid Mapping of Populated Indoor Scenes using a Low-Cost Monocular UAV
Stuart Golodetz, Madhu Vankadari, Aluna Everitt +3
Unmanned aerial vehicles (UAVs) have been used for many applications in recent years, from urban search and rescue, to agricultural surveying, to autonomous underground mine explor…
SensatUrban: Learning Semantics from Urban-Scale Photogrammetric Point Clouds
Qingyong Hu, Bo Yang, Sheikh Khalid +3
With the recent availability and affordability of commercial depth sensors and 3D scanners, an increasing number of 3D (i.e., RGBD, point cloud) datasets have been publicized to fa…
Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction
Ta-Ying Cheng, Hsuan-Ru Yang, Niki Trigoni +2
We present a pose adaptive few-shot learning procedure and a two-stage data interpolation regularization, termed Pose Adaptive Dual Mixup (PADMix), for single-image 3D reconstructi…
Learning Semantic Segmentation of Large-Scale Point Clouds with Random Sampling
Qingyong Hu, Bo Yang, Linhai Xie +5
We study the problem of efficient semantic segmentation of large-scale 3D point clouds. By relying on expensive sampling techniques or computationally heavy pre/post-processing ste…
Graph-based Thermal-Inertial SLAM with Probabilistic Neural Networks
Muhamad Risqi U. Saputra, Chris Xiaoxuan Lu, Pedro P. B. de Gusmao +3
Simultaneous Localization and Mapping (SLAM) system typically employ vision-based sensors to observe the surrounding environment. However, the performance of such systems highly de…
SQN: Weakly-Supervised Semantic Segmentation of Large-Scale 3D Point Clouds
Qingyong Hu, Bo Yang, Guangchi Fang +4
Labelling point clouds fully is highly time-consuming and costly. As larger point cloud datasets with billions of points become more common, we ask whether the full annotation is e…