Check out our #CVPR2022 paper "LISA: Learning Implicit Shape and Appearance of Hands". We proposed a do-it-all neural hand model, which captures accurate hand shape, pose, appearance, correspondences and generalize to arbitrary new subjects! project page: iri.upc.edu/people/ecorona…

"Desktop Activities" is public as part of #projectaria pilot dataset! Hope this synchronized egocentric vision and multi-view mocap dataset can help the community to work on human-objects understanding 💪 Ground truth annotation will soon be available! facebookresearch.github.io/Aria_data_tool…

Andrew Marmon and I rounded up all #CVPR2022 papers on NeRF/Neural Radiance Fields we could find in a new blog post here: dellaert.github.io/NeRF22/

#CVPR2022 Best Paper Awards

If you're still at CVPR and have the stamina to make it through another poster session, check out RawNeRF tomorrow morning! We exploit the fact that NeRF is surprisingly robust to image noise to reconstruct scenes directly from raw HDR sensor data.

We'll be presenting our poster today at 177b from 14:30 - 17:00, check it out if you're at #CVPR2022!

Excited to share our ECCV 2022 paper which estimates the 6D object poses by learning a dense 3D correspondence field.

#CVPR2023 June 22, Thu AM (Poster 57) In-Hand 3D Object Scanning From an RGB Sequence Shreyas Hampali, Tomáš Hodaň, Luan Tran, Lingni Ma, Cem Keskin, VincentLepetit pdf: arxiv.org/abs/2211.16193

For #CVPR2023, we have a nice little magic trick. MIME takes 3D human motion capture and generates plausible 3D scenes that are consistent with the motion. Why? Most mocap sessions capture the person but not the scene.

Excellent new fine-grained tracking from DeepMind: TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement arxiv: arxiv.org/abs/2306.08637 project: deepmind-tapir.github.io tldr: TapNet for localization then PIPs-style refinement; outperforms everything!

MotionGPT: Finetuned LLMs are General-Purpose Motion Generators paper page: huggingface.co/papers/2306.10… Generating realistic human motion from given action descriptions has experienced significant advancements because of the emerging requirement of digital humans. While recent

MotionGPT: Human Motion as a Foreign Language paper page: huggingface.co/papers/2306.14… Though the advancement of pre-trained large language models unfolds, the exploration of building a unified model for language and other multi-modal data, such as motion, remains challenging and

Happy new year everyone! Super excited to announce that our workshop proposal #EgoMotion is accepted #CVPR2024! This will be the 1st workshop on egocentric human motion tracking, synthesis and action recognition. Please stay tuned for more updates & see you all in Seattle!

EgoMotion workshop happening now🔥 Richard Newcombe is giving the opening talk in room Summit429

Released by Reality Labs at Meta Research at #ECCV2024, Nymeria is a large-scale multimodal egocentric dataset for full-body motion understanding with potential applications in VR/MR headsets, smart glasses and more. More on this work + access to the dataset ➡️ go.fb.me/0znnvb

Introducing Aria Gen 2, next generation glasses that we hope will enable researchers from industry and academia to unlock new work in machine perception, contextual AI, robotics and more. Aria Gen 2 details + sign up for availability updates ➡️ go.fb.me/8rku3b