3D reconstruction of articulated objects from a single image is challenging because large training datasets with paired image and 3D supervision are difficult to obtain. Recent point map-based methods achieve strong performance but rely on synthetic datasets rendered from manually created articulated 3D assets with carefully curated pose distributions.
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Mac Aodha
Computer Science > Computer Vision and Pattern Recognition
Autonomous scientific discovery systems offer the potential to accelerate research by automating the process of hypothesis generation and validation. However, current systems operate within constrained search spaces or require predefined research questions, limiting their capacity for true open-ended inquiry.
APRES: An Agentic Paper Revision and Evaluation System
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
BiMotion: B-spline Motion for Text-guided Dynamic 3D Character Generation
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
MotionPhysics: Learnable Motion Distillation for Text-Guided Simulation
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
INQUIRE-Search: A Framework for Interactive Discovery in Large-Scale Biodiversity Databases
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Attentive Feature Aggregation or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2510.21609] Enhancing Tactile-based Reinforcement Learning for Robotic Control
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
The Automated LLM Speedrunning Benchmark: Reproducing NanoGPT Improvements
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Electrical Engineering and Systems Science > Image and Video Processing
[Submitted on 19 Jun 2025 (v1), last revised 7 Oct 2026 (this version, v2)] View PDF HTML (experimental) Subjects: Image and Video Processing (eess.IV); Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2506.16556 [eess.IV] (or arXiv:2506.16556v2 [eess.IV] for this version) https://doi.org/10.48550/arXiv.2506.16556 Journal reference: International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), 2025
[2505.23917] Representational Difference Explanations
arXiv:2505.23917 (cs) View PDF Comments: Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neurons and Cognition (q-bio.NC) Cite as: arXiv:2505.23917 [cs.CV] (or arXiv:2505.23917v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2505.23917 Submission history From: Neehar Kondapaneni [ view email] [v1] Thu, 29 May 2025 18:09:44 UTC (8,424 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer ()...
MVSAnywhere: Zero-Shot Multi-View Stereo
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2503.15699] Representational Similarity via Interpretable Visual Concepts
arXiv:2503.15699 (cs) View PDF Comments: Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Neurons and Cognition (q-bio.NC) Cite as: arXiv:2503.15699 [cs.CV] (or arXiv:2503.15699v1 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2503.15699 Submission history From: Neehar Kondapaneni [ view email] [v1] Wed, 19 Mar 2025 21:21:45 UTC (8,021 KB) Bibliographic Tools Bibliographic Explorer Toggle Bibliographic Explorer () Connected Papers Toggle...
[2502.14977] Few-shot Species Range Estimation
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
acoupi: An Open-Source Python Framework for Deploying Bioacoustic AI Models on Edge Devices
[Submitted on 29 Jan 2025] Title:acoupi: An Open-Source Python Framework for Deploying Bioacoustic AI Models on Edge Devices View a PDF of the paper titled acoupi: An Open-Source Python Framework for Deploying Bioacoustic AI Models on Edge Devices, by Aude Vuilliomenet and 4 other authors View PDF HTML (experimental) Abstract:1. Passive acoustic monitoring (PAM) coupled with artificial intelligence (AI) is becoming an essential tool for biodiversity monitoring.
CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections
[Submitted on 5 Dec 2024] Title:CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections View a PDF of the paper titled CrossSDF: 3D Reconstruction of Thin Structures From Cross-Sections, by Thomas Walker and 6 other authors View PDF HTML (experimental) Abstract:Reconstructing complex structures from planar cross-sections is a challenging problem, with wide-reaching applications in medical imaging, manufacturing, and topography.
[2408.15956] Generating Binary Species Range Maps
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2408.14348] Deep learning-based ecological analysis of camera trap images is impacted by training data quality and quantity
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2406.04898] Labeled Data Selection for Category Discovery
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
GeoGen: Geometry-Aware Generative Modeling via Signed Distance Functions
[Submitted on 6 Jun 2024] Title:GeoGen: Geometry-Aware Generative Modeling via Signed Distance Functions View a PDF of the paper titled GeoGen: Geometry-Aware Generative Modeling via Signed Distance Functions, by Salvatore Esposito and 8 other authors View PDF HTML (experimental) Abstract:We introduce a new generative approach for synthesizing 3D geometry and images from single-view collections. Most existing approaches predict volumetric density to render multi-view consistent images.
[2406.02535] Enhancing 2D Representation Learning with a 3D Prior
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Robertson, Colin (2016): Mulltilingual Law: A Framework for Analysis and Understanding. London: Routledge, 273 p.
IdiomacatalàDeutschEnglishespañoleuskarafrançaisgalegoitalianoportuguêsromână
[2312.13216] Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2311.02061] Active Learning-Based Species Range Estimation
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Whombat: An open-source annotation tool for machine learning development in bioacoustics
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
[2305.07014] Virtual Occlusions Through Implicit Depth
arXiv:2305.07014 (cs) Download a PDF of the paper titled Virtual Occlusions Through Implicit Depth, by Jamie Watson and Mohamed Sayed and Zawar Qureshi and Gabriel J.
[2304.14310] Incremental Generalized Category Discovery
arXiv:2304.14310 (cs) [Submitted on 27 Apr 2023 (v1), last revised 7 Dec 2023 (this version, v3)] Download PDF HTML (experimental) Comments: Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2304.14310 [cs.CV] (or arXiv:2304.14310v3 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2304.14310 Submission history From: Bingchen Zhao [ view email] [v1] Thu, 27 Apr 2023 16:27:11 UTC (5,896 KB) [v2] Thu, 17 Aug 2023 14:01:03 UTC (8,476 KB) [v3] Thu, 7 Dec 2023...
[2304.01008] Self-Supervised Multimodal Learning: A Survey
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
SAOR: Single-View Articulated Object Reconstruction
arXiv:2303.13514 (cs) [Submitted on 23 Mar 2023 (v1), last revised 1 Dec 2023 (this version, v2)] Download PDF Comments: Subjects: Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2303.13514 [cs.CV] (or arXiv:2303.13514v2 [cs.CV] for this version) https://doi.org/10.48550/arXiv.2303.13514 Submission history From: Mehmet Aygün [ view email] [v1] Thu, 23 Mar 2023 17:59:35 UTC (12,094 KB) [v2] Fri, 1 Dec 2023 19:25:10 UTC (17,738 KB) Bibliographic Tools Bibliographic Explorer...
Bat Detective - Deep learning tools for bat acoustic signal detection
Mac Aodha, O; Gibb, R; Barlow, KE; Browning, E; Firman, M; Freeman, R; Harder, B; ... Jones, KE; + view all Mac Aodha, O; Gibb, R; Barlow, KE; Browning, E; Firman, M; Freeman, R; Harder, B; Kinsey, L; Mead, GR; Newson, SE; Pandourski, I; Parsons, S; Russ, J; Szodoray-Paradi, A; Szodoray-Paradi, F; Tilova, E; Girolami, M; Brostow, G; Jones, KE; - view fewer (2018) Bat Detective - Deep learning tools for bat acoustic signal detection. PLoS Computational Biology (In press).
Unsupervised Monocular Depth Estimation with Left-Right Consistency
Godard, C; Mac Aodha, O; Brostow, GJ; (2017) Unsupervised Monocular Depth Estimation with Left-Right Consistency. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). (pp. pp. 6602-6611). IEEE: Honolulu, HI, USA. Learning based methods have shown very promising results for the task of depth estimation in single images.
[1710.01691] Context Embedding Networks
Abstract: Low dimensional embeddings that capture the main variations of interest in collections of data are important for many applications. One way to construct these embeddings is to acquire estimates of similarity from the crowd. However, similarity is a multi-dimensional concept that varies from individual to individual.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Mac
Contact Mac, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack