Tomas Jakab

26 papers A* 6Journal 15Unranked 5
YearRankTypeTitle / Venue / Authors
2025 — conf
DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer.
3DV
Runjia Li, Junlin Han, Luke Melas-Kyriazi, Chunyi Sun, Zhaochong An, Zhongrui Gui, Shuyang Sun, Philip Torr, Tomas Jakab
2025 — conf
DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors.
ICCVW
Hanwen Zhu, Ruining Li, Tomas Jakab
2025 A* conf
DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction.
CVPR
Ben Kaye, Tomas Jakab, Shangzhe Wu, Christian Ruprecht, Andrea Vedaldi
2025 J jnl
EgoEdit: Dataset, Real-Time Streaming Model, and Benchmark for Egocentric Video Editing.
CoRR
Runjia Li, Moayed Haji-Ali, Ashkan Mirzaei, Chaoyang Wang, Arpit Sahni, Ivan Skorokhodov, Aliaksandr Siarohin, Tomas Jakab, Junlin Han, Sergey Tulyakov, Philip Torr, Willi Menapace
2025 J jnl
VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory.
CoRR
Runjia Li, Philip Torr, Andrea Vedaldi, Tomas Jakab
2024 J jnl
DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer.
CoRR
Runjia Li, Junlin Han, Luke Melas-Kyriazi, Chunyi Sun, Zhaochong An, Zhongrui Gui, Shuyang Sun, Philip Torr, Tomas Jakab
2024 J jnl
DreamHOI: Subject-Driven Generation of 3D Human-Object Interactions with Diffusion Priors.
CoRR
Thomas Hanwen Zhu, Ruining Li, Tomas Jakab
2024 J jnl
DualPM: Dual Posed-Canonical Point Maps for 3D Shape and Pose Reconstruction.
CoRR
Ben Kaye, Tomas Jakab, Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi
2024 — conf
Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion.
3DV
Tomas Jakab, Ruining Li, Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi
2024 — conf
Instant Uncertainty Calibration of NeRFs Using a Meta-calibrator.
ECCV (78)
Niki Amini-Naieni, Tomas Jakab, Andrea Vedaldi, Ronald Clark
2024 A* conf
Learning the 3D Fauna of the Web.
CVPR
Zizhang Li, Dor Litvak, Ruining Li, Yunzhi Zhang, Tomas Jakab, Christian Rupprecht, Shangzhe Wu, Andrea Vedaldi, Jiajun Wu
2024 J jnl
Learning the 3D Fauna of the Web.
CoRR
Zizhang Li, Dor Litvak, Ruining Li, Yunzhi Zhang, Tomas Jakab, Christian Rupprecht, Shangzhe Wu, Andrea Vedaldi, Jiajun Wu
2024 — conf
Scene-Conditional 3D Object Stylization and Composition.
ECCV (68)
Jinghao Zhou, Tomas Jakab, Philip Torr, Christian Rupprecht
2023 J jnl
Calibrated Uncertainties for Neural Radiance Fields.
CoRR
Niki Amini-Naieni, Tomas Jakab, Andrea Vedaldi, Ronald Clark
2023 J jnl
DOVE: Learning Deformable 3D Objects by Watching Videos.
Int. J. Comput. Vis.
Shangzhe Wu, Tomas Jakab, Christian Rupprecht, Andrea Vedaldi
2023 J jnl
Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion.
CoRR
Tomas Jakab, Ruining Li, Shangzhe Wu, Christian Rupprecht, Andrea Vedaldi
2023 A* conf
MagicPony: Learning Articulated 3D Animals in the Wild.
CVPR
Shangzhe Wu, Ruining Li, Tomas Jakab, Christian Rupprecht, Andrea Vedaldi
2023 J jnl
Scene-Conditional 3D Object Stylization and Composition.
CoRR
Jinghao Zhou, Tomas Jakab, Philip Torr, Christian Rupprecht
2022 J jnl
MagicPony: Learning Articulated 3D Animals in the Wild.
CoRR
Shangzhe Wu, Ruining Li, Tomas Jakab, Christian Rupprecht, Andrea Vedaldi
2021 J jnl
DOVE: Learning Deformable 3D Objects by Watching Videos.
CoRR
Shangzhe Wu, Tomas Jakab, Christian Rupprecht, Andrea Vedaldi
2021 A* conf
KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control.
CVPR
Tomas Jakab, Richard Tucker, Ameesh Makadia, Jiajun Wu, Noah Snavely, Angjoo Kanazawa
2021 J jnl
KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control.
CoRR
Tomas Jakab, Richard Tucker, Ameesh Makadia, Jiajun Wu, Noah Snavely, Angjoo Kanazawa
2020 A* conf
Self-Supervised Learning of Interpretable Keypoints From Unlabelled Videos.
CVPR
Tomas Jakab, Ankush Gupta, Hakan Bilen, Andrea Vedaldi
2019 J jnl
Learning Landmarks from Unaligned Data using Image Translation.
CoRR
Tomas Jakab, Ankush Gupta, Hakan Bilen, Andrea Vedaldi
2018 J jnl
Conditional Image Generation for Learning the Structure of Visual Objects.
CoRR
Tomas Jakab, Ankush Gupta, Hakan Bilen, Andrea Vedaldi
2018 A* conf
Unsupervised Learning of Object Landmarks through Conditional Image Generation.
NeurIPS
Tomas Jakab, Ankush Gupta, Hakan Bilen, Andrea Vedaldi