Accepted to IEEE Access.</p>\n","updatedAt":"2026-09-17T02:36:36.943Z","author":{"_id":"639c144bf44c46d8af63b8f9","avatarUrl":"/avatars/de32f82f4befd43e3f9099e6ed6345a1.svg","fullname":"Ryosei Hara","name":"ryhara","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":1,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.959222137928009},"editors":["ryhara"],"editorAvatarUrls":["/avatars/de32f82f4befd43e3f9099e6ed6345a1.svg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2609.17189","authors":[{"_id":"6aab51f71d9cc4dec796243e","user":{"_id":"639c144bf44c46d8af63b8f9","avatarUrl":"/avatars/de32f82f4befd43e3f9099e6ed6345a1.svg","isPro":false,"fullname":"Ryosei Hara","user":"ryhara","type":"user","name":"ryhara"},"name":"Ryosei Hara","status":"claimed_verified","statusLastChangedAt":"2026-09-17T08:45:04.475Z","hidden":false},{"_id":"6aab51f71d9cc4dec796243f","name":"Wataru Ikeda","hidden":false},{"_id":"6aab51f71d9cc4dec7962440","name":"Masashi Hatano","hidden":false},{"_id":"6aab51f71d9cc4dec7962441","name":"Mariko Isogawa","hidden":false}],"publishedAt":"2026-09-15T00:00:00.000Z","submittedOnDailyAt":"2026-09-17T00:00:00.000Z","title":"EventEgoHands++: Event-based Egocentric 3D Hand Mesh Reconstruction with Real Dataset","submittedOnDailyBy":{"_id":"639c144bf44c46d8af63b8f9","avatarUrl":"/avatars/de32f82f4befd43e3f9099e6ed6345a1.svg","isPro":false,"fullname":"Ryosei Hara","user":"ryhara","type":"user","name":"ryhara"},"summary":"3D hand mesh reconstruction is a challenging yet essential task for downstream applications, including human-robot interaction and AR/VR. Although conventional cameras have been widely adopted for this task, methods that rely on them struggle in low-light environments and under severe motion blur. To address these limitations, event-based cameras have recently attracted attention for their high dynamic range and high temporal resolution. However, applying event cameras to egocentric hand reconstruction remains challenging because camera wearer's motion produces dense background events that obscure hand-specific signals. Although the first egocentric event-based approach mitigates this issue using hand segmentation, its binary hand mask does not distinguish between left and right hands. As a result, the model lacks instance-level hand information and predicts both hands even when only one or neither hand is present. This limitation leads to incorrect inter-hand relationships and degraded reconstruction accuracy. In this paper, we propose EventEgoHands++, a framework for event-based 3D hand mesh reconstruction from an egocentric viewpoint. The proposed method incorporates a Hand Detector that estimates instance-level bounding boxes and masks for both the left and right hands. Moreover, we introduce Adaptive Attention, which dynamically gates the attention based on these detection results to accurately learn the spatial relationship and mutual interactions between the hands. To train and evaluate our framework, we extend the synthetic N-HOT3D dataset and newly construct EEH-R, the largest real-world event-based egocentric hand dataset to date, comprising approximately 1M annotated frames captured in environments including low-light conditions. Extensive experiments on both synthetic and real datasets demonstrate that our method consistently outperforms the baselines.","upvotes":21,"discussionId":"6aab51f71d9cc4dec7962442","projectPage":"https://ryhara.github.io/EventEgoHandsV2/","githubRepo":"https://github.com/ryhara/EventEgoHandsV2","githubRepoAddedBy":"user","githubStars":6},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"639c144bf44c46d8af63b8f9","avatarUrl":"/avatars/de32f82f4befd43e3f9099e6ed6345a1.svg","isPro":false,"fullname":"Ryosei Hara","user":"ryhara","type":"user"},{"_id":"6a6a91ad4e0203edaf1f7ae6","avatarUrl":"/avatars/764cfb5bc47dbfca6d720260a64cfe16.svg","isPro":false,"fullname":"Patricia Rodriguez","user":"patricia-rodriguez","type":"user"},{"_id":"6a6a9b6cd3e6cc76822373e9","avatarUrl":"/avatars/7a93065f42475ca37c70031b6031f694.svg","isPro":false,"fullname":"James White","user":"wildreed","type":"user"},{"_id":"6a6c8284e1fe45d02066a1ea","avatarUrl":"/avatars/f30b813d418d7d93f58ae3691fcda2c9.svg","isPro":false,"fullname":"Andrew Garcia","user":"cedarloom","type":"user"},{"_id":"6a6c83c8bd71e954a590ca0d","avatarUrl":"/avatars/fa4e69ebce443312d7b1962d551b29d7.svg","isPro":false,"fullname":"Barbara Brown","user":"GraniteLens","type":"user"},{"_id":"6a6c8e41ddefa50419e0eab4","avatarUrl":"/avatars/f7731c21169091f5386a4e3712366620.svg","isPro":false,"fullname":"Richard Johnson","user":"Indigo-Mika","type":"user"},{"_id":"6a6aa148ad5a6f2f63620596","avatarUrl":"/avatars/11497c4cb1c583ebe22f266fa8585e92.svg","isPro":false,"fullname":"David Williams","user":"Indigo-Scope","type":"user"},{"_id":"6a6de3b46d51d01100d6f251","avatarUrl":"/avatars/2441a21df4bfc94a281baded48b88c8b.svg","isPro":false,"fullname":"Barbara Perez","user":"barbara-perez","type":"user"},{"_id":"6a701c6c518039c9718c3b96","avatarUrl":"/avatars/2e6fa06a429776f305200495892836d6.svg","isPro":false,"fullname":"Daniel Martinez","user":"MeridianLens","type":"user"},{"_id":"6a701f31925462dc3ad8ceea","avatarUrl":"/avatars/bdde8118bd8007bce40748b45c446d07.svg","isPro":false,"fullname":"Patricia Taylor","user":"meridianpulse","type":"user"},{"_id":"6a811547dc776a4d223eea7b","avatarUrl":"/avatars/064dd5f5ead4dc0b128a2884d31b06c0.svg","isPro":false,"fullname":"yuxuan sun","user":"Nova-Yuxuan617","type":"user"},{"_id":"6a9ae275c3a3d75ba18a0df8","avatarUrl":"/avatars/9a5fd2286fc550d4de7efcff6c2523f1.svg","isPro":false,"fullname":"Danielle Payne","user":"jennylester","type":"user"}],"acceptLanguages":["en"],"dailyPaperRank":0,"markdownContentUrl":"https://huggingface.co/buckets/huggingchat/papers-content/resolve/2609/2609.17189.md","query":{}}">
EventEgoHands++: Event-based Egocentric 3D Hand Mesh Reconstruction with Real Dataset
Abstract
3D hand mesh reconstruction is a challenging yet essential task for downstream applications, including human-robot interaction and AR/VR. Although conventional cameras have been widely adopted for this task, methods that rely on them struggle in low-light environments and under severe motion blur. To address these limitations, event-based cameras have recently attracted attention for their high dynamic range and high temporal resolution. However, applying event cameras to egocentric hand reconstruction remains challenging because camera wearer's motion produces dense background events that obscure hand-specific signals. Although the first egocentric event-based approach mitigates this issue using hand segmentation, its binary hand mask does not distinguish between left and right hands. As a result, the model lacks instance-level hand information and predicts both hands even when only one or neither hand is present. This limitation leads to incorrect inter-hand relationships and degraded reconstruction accuracy. In this paper, we propose EventEgoHands++, a framework for event-based 3D hand mesh reconstruction from an egocentric viewpoint. The proposed method incorporates a Hand Detector that estimates instance-level bounding boxes and masks for both the left and right hands. Moreover, we introduce Adaptive Attention, which dynamically gates the attention based on these detection results to accurately learn the spatial relationship and mutual interactions between the hands. To train and evaluate our framework, we extend the synthetic N-HOT3D dataset and newly construct EEH-R, the largest real-world event-based egocentric hand dataset to date, comprising approximately 1M annotated frames captured in environments including low-light conditions. Extensive experiments on both synthetic and real datasets demonstrate that our method consistently outperforms the baselines.
Community
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
Cite arxiv.org/abs/2609.17189 in a model README.md to link it from this page.
Cite arxiv.org/abs/2609.17189 in a dataset README.md to link it from this page.
Cite arxiv.org/abs/2609.17189 in a Space README.md to link it from this page.
Discussion (0)
Sign in to join the discussion. Free account, 30 seconds — email code or GitHub.
Sign in →No comments yet. Sign in and be the first to say something.