GP
Georgios Pavlakos
cs.CVcs.ROcs.GRcs.AIcs.LGChild DevelopmentHandInfancyKinematicsPreshaping
On Valency
published · living versionsW_7vbj8eng·v1 · currentpublished
AgiWorld: An Agentic Video World Model for Building Persistent Worlds
with Shaoheng Fang, Yiqun Mei, Hanwen Jiang, Xin Sun +5
1 version
Preprints & journals
58 papers in the corpus · 2016–2026StableGrasp: Reconstructing Physically Stable Human Hand Grasps from Single Images2610.09195v1 · Han Jiang, Etienne Vouga, Qixing Huang et al.2026 · 0 citationsarXiv
Ego-Exo4D Human Meshes Dataset: 4D Human Motion Reconstruction for Ego-Exo Captures2609.30187v1 · Abhiram Maddukuri, Georgios Pavlakos2026 · 0 citationsarXiv
Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model2608.29928v1 · R. James Cotton, J.D. Peiffer, Lucinda Williamson et al.2026 · 0 citationsarXiv
Reconstructing Humans and Objects in Interaction using Large Reconstruction Models2608.27407v1 · Agniv Chatterjee, Georgios Pavlakos2026 · 0 citationsComputer Vision - ECCV 2026, Lecture Notes in Computer Science, vol 17037, pp. 37-57, Springer, Cham (2026)
Dynamics of infant preshaping: Longitudinal analysis using automated hand pose tracking from home video.42636601 · Campbell, Kaitlyn, Horger, Melissa N, Pavlakos, Georgios et al.2026 · 0 citationsInfant behavior & development. 2026;84:102232
ARAPDiffusion: Geometry-Distribution Feedback for Deformable 3D Shape Generation2606.06887v2 · Haibo Liu, Jinghan Ke, Haitao Yang et al.2026 · 0 citationsarXiv
Recovering Physically Plausible Human-Object Interactions from Monocular Videos2606.05359v1 · Dingbang Huang, Etienne Vouga, Qixing Huang et al.2026 · 0 citationsarXiv
HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image2606.02573v1 · Hezhen Hu, Wangbo Zhao, Lanqing Guo et al.2026 · 0 citationsarXiv
Natural Human Motion Recovery by Aligning High-Order Temporal Dynamics from Monocular Videos2605.26879v1 · Dingkun Wei, Zehong Shen, Yan Xia et al.2026 · 0 citationsarXiv
Age-Inclusive 3D Human Mesh Recovery for Action-Preserving Data Anonymization2512.05259v1 · Georgios Chatzichristodoulou, Niki Efthymiou, Panagiotis Filntisis et al.2025 · 0 citationsarXiv
Searching in Space and Time: Unified Memory-Action Loops for Open-World Object Retrieval2511.14004v3 · Taijing Chen, Sateesh Kumar, Junhong Xu et al.2025 · 0 citationsarXiv
Enhancing Monocular 3D Hand Reconstruction with Learned Texture Priors2508.09629v2 · Giorgos Karvounas, Nikolaos Kyriazis, Iason Oikonomidis et al.2025 · 0 citationsarXiv
COLLAGE: Adaptive Fusion-based Retrieval for Augmented Policy Learning2508.01131v2 · Sateesh Kumar, Shivin Dass, Georgios Pavlakos et al.2025 · 0 citationsarXiv
RayZer: A Self-supervised Large View Synthesis Model2505.00702v1 · Hanwen Jiang, Hao Tan, Peng Wang et al.2025 · 14 citationsarXiv
Reconstructing Humans with a Biomechanically Accurate Skeleton2503.21751v1 · Yan Xia, Xiaowei Zhou, Etienne Vouga et al.2025 · 17 citationsarXiv
MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data2412.14166v2 · Hanwen Jiang, Zexiang Xu, Desai Xie et al.2024 · 6 citationsarXiv
FIction: 4D Future Interaction Prediction from Video2412.00932v2 · Kumar Ashutosh, Georgios Pavlakos, Kristen Grauman2024 · 2 citationsarXiv
OKAMI: Teaching Humanoid Robots Manipulation Skills through Single Video Imitation2410.11792v1 · Jinhan Li, Yifeng Zhu, Yuqi Xie et al.2024 · 3 citationsarXiv
Estimating Body and Hand Motion in an Ego-sensed World2410.03665v3 · Brent Yi, Vickie Ye, Maya Zheng et al.2024 · 11 citationsarXiv
Synergy and Synchrony in Couple Dances2409.04440v1 · Vongani Maluleke, Lea Muller, Jathushan Rajasegaran et al.2024 · 0 citationsarXiv
Atlas Gaussians Diffusion for 3D Generation2408.13055v3 · Haitao Yang, Yuan Dong, Hanwen Jiang et al.2024 · 0 citationsarXiv
ExpertAF: Expert Actionable Feedback from Video2408.00672v3 · Kumar Ashutosh, Tushar Nagarajan, Georgios Pavlakos et al.2024 · 20 citationsarXiv
Expressive Gaussian Human Avatars from Monocular RGB Video2407.03204v1 · Hezhen Hu, Zhiwen Fan, Tianhao Wu et al.2024 · 10 citationsarXiv
Real3D: Scaling Up Large Reconstruction Models with Real-World Images2406.08479v1 · Hanwen Jiang, Qixing Huang, Georgios Pavlakos2024 · 1 citationarXiv
CoFie: Learning Compact Neural Surface Representations with Coordinate Fields2406.03417v1 · Hanwen Jiang, Haitao Yang, Georgios Pavlakos et al.2024 · 1 citationarXiv
Evaluating Zero-Shot GPT-4V Performance on 3D Visual Question Answering Benchmarks2405.18831v1 · Simranjit Singh, Georgios Pavlakos, Dimitrios Stamoulis2024 · 1 citationarXiv
MultiPhys: Multi-Person Physics-aware 3D Motion Estimation2404.11987v1 · Nicolas Ugrinovic, Boxiao Pan, Georgios Pavlakos et al.2024 · 7 citationsarXiv
Reconstructing Hand-Held Objects in 3D from Images and Videos2404.06507v4 · Jane Wu, Georgios Pavlakos, Georgia Gkioxari et al.2024 · 1 citationarXiv
InstantSplat: Sparse-view Gaussian Splatting in Seconds2403.20309v6 · Zhiwen Fan, Wenyan Cong, Kairun Wen et al.2024 · 16 citationsarXiv
Reconstructing Hands in 3D with Transformers2312.05251v1 · Georgios Pavlakos, Dandan Shan, Ilija Radosavovic et al.2023 · 165 citationsarXiv
GART: Gaussian Articulated Template Models2311.16099v1 · Jiahui Lei, Yufu Wang, Georgios Pavlakos et al.2023 · 111 citationsarXiv
Generative Proxemics: A Prior for 3D Social Interaction from Images2306.09337v2 · Lea Muller, Vickie Ye, Georgios Pavlakos et al.2023 · 25 citationsarXiv
Humans in 4D: Reconstructing and Tracking Humans with Transformers2305.20091v3 · Shubham Goel, Georgios Pavlakos, Jathushan Rajasegaran et al.2023 · 275 citationsarXiv
Learning Articulated Shape with Keypoint Pseudo-labels from Web Images2304.14396v1 · Anastasis Stathopoulos, Georgios Pavlakos, Ligong Han et al.2023 · 7 citationsarXiv
On the Benefits of 3D Pose and Tracking for Human Action Recognition2304.01199v2 · Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa et al.2023 · 50 citationsarXiv
Decoupling Human and Camera Motion from Videos in the Wild2302.12827v2 · Vickie Ye, Georgios Pavlakos, Jitendra Malik et al.2023 · 84 citationsarXiv
The One Where They Reconstructed 3D Humans and Environments in TV Shows2207.14279v1 · Georgios Pavlakos, Ethan Weber, Matthew Tancik et al.2022 · 23 citationsarXiv
Semantic keypoint-based pose estimation from single RGB frames2204.05864v1 · Karl Schmeckpeper, Philip R. Osteen, Yufu Wang et al.2022 · 8 citationsField Robotics, 2, 147-171, 2022
Tracking People by Predicting 3D Appearance, Location & Pose2112.04477v1 · Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa et al.2021 · 0 citationsarXiv
Tracking People with 3D Representations2111.07868v1 · Jathushan Rajasegaran, Georgios Pavlakos, Angjoo Kanazawa et al.2021 · 12 citationsarXiv
Probabilistic Modeling for Human Mesh Recovery2108.11944v1 · Nikos Kolotouros, Georgios Pavlakos, Dinesh Jayaraman et al.2021 · 164 citationsarXiv
Human Mesh Recovery from Multiple Shots2012.09843v1 · Georgios Pavlakos, Jitendra Malik, Angjoo Kanazawa2020 · 54 citationsarXiv
Independent Sign Language Recognition with 3D Body, Hands, and Face Reconstruction2012.05698v1 · Agelos Kratimenos, Georgios Pavlakos, Petros Maragos2020 · 21 citationsarXiv
Monocular Expressive Body Regression through Body-Driven Attention2008.09062v1 · Vasileios Choutas, Georgios Pavlakos, Timo Bolkart et al.2020 · 244 citationsarXiv
Coherent Reconstruction of Multiple Humans from a Single Image2006.08586v1 · Wen Jiang, Nikos Kolotouros, Georgios Pavlakos et al.2020 · 177 citationsarXiv
Technical Report: Reactive Semantic Planning in Unexplored Semantic Environments Using Deep Perceptual Feedback2002.12349v3 · Vasileios Vasilopoulos, Georgios Pavlakos, Sean L. Bowman et al.2020 · 1 citationarXiv
Reactive Navigation in Partially Familiar Planar Environments Using Semantic Perceptual Feedback2002.08946v2 · Vasileios Vasilopoulos, Georgios Pavlakos, Karl Schmeckpeper et al.2020 · 26 citationsarXiv
TexturePose: Supervising Human Mesh Estimation with Texture Consistency1910.11322v1 · Georgios Pavlakos, Nikos Kolotouros, Kostas Daniilidis2019 · 112 citationsarXiv
Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop1909.12828v1 · Nikos Kolotouros, Georgios Pavlakos, Michael J. Black et al.2019 · 1,046 citationsarXiv
Convolutional Mesh Regression for Single-Image Human Shape Reconstruction1905.03244v1 · Nikos Kolotouros, Georgios Pavlakos, Kostas Daniilidis2019 · 563 citationsarXiv
Career total: 74 works. 58 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.