# Hand-4DGS: Feed-Forward 3D Gaussian Splatting for 4D Hand Reconstruction from Egocentric Videos

arXiv: https://arxiv.org/abs/2606.19156 · HTML: https://mlsanity.com/paper/2606.19156/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 57 of its 68 references that are in the map.
- First posted on arXiv 17 Jun 2026.

## Builds on (most cited first, 30 of 57)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [SAM 3: Segment Anything with Concepts](https://mlsanity.com/paper/2511.16719/) (2025)
- [pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction](https://mlsanity.com/paper/2312.12337/) (2023)
- [MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images](https://mlsanity.com/paper/2403.14627/) (2024)
- [Rescaling Egocentric Vision](https://mlsanity.com/paper/2006.13256/) (2020)
- [Zero-Shot Text-Guided Object Generation with Dream Fields](https://mlsanity.com/paper/2112.01455/) (2021)
- [Learning joint reconstruction of hands and manipulated objects](https://mlsanity.com/paper/1904.05767/) (2019)
- [Humans in 4D: Reconstructing and Tracking Humans with Transformers](https://mlsanity.com/paper/2305.20091/) (2023)
- [ARCTIC: A Dataset for Dexterous Bimanual Hand-Object Manipulation](https://mlsanity.com/paper/2204.13662/) (2022)
- [Reconstructing Hands in 3D with Transformers](https://mlsanity.com/paper/2312.05251/) (2023)
- [H2O: Two Hands Manipulating Objects for First Person Interaction Recognition](https://mlsanity.com/paper/2104.11181/) (2021)
- [GPS-Gaussian: Generalizable Pixel-wise 3D Gaussian Splatting for Real-time Human Novel View Synthesis](https://mlsanity.com/paper/2312.02155/) (2023)
- [FrankMocap: A Monocular 3D Whole-Body Pose Estimation System via Regression and Integration](https://mlsanity.com/paper/2108.06428/) (2021)
- [HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World](https://mlsanity.com/paper/2309.17024/) (2023)
- [HUGS: Human Gaussian Splats](https://mlsanity.com/paper/2311.17910/) (2023)
- [Reconstructing Hand-Object Interactions in the Wild](https://mlsanity.com/paper/2012.09856/) (2020)
- [L4GM: Large 4D Gaussian Reconstruction Model](https://mlsanity.com/paper/2406.10324/) (2024)
- [Semi-Supervised 3D Hand-Object Poses Estimation with Interactions in Time](https://mlsanity.com/paper/2106.05266/) (2021)
- [WiLoR: End-to-end 3D Hand Localization and Reconstruction in-the-wild](https://mlsanity.com/paper/2409.12259/) (2024)
- [Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image](https://mlsanity.com/paper/2406.04343/) (2024)
- [TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding](https://mlsanity.com/paper/2401.08399/) (2024)
- [Interacting Attention Graph for Single Image Two-Hand Reconstruction](https://mlsanity.com/paper/2203.09364/) (2022)
- [HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video](https://mlsanity.com/paper/2311.18448/) (2023)
- [HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos](https://mlsanity.com/paper/2501.02973/) (2025)
- [IDOL: Instant Photorealistic 3D Human Creation from a Single Image](https://mlsanity.com/paper/2412.14963/) (2024)
- [HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors](https://mlsanity.com/paper/2406.12459/) (2024)
- [Dyn-HaMR: Recovering 4D Interacting Hand Motion from a Dynamic Camera](https://mlsanity.com/paper/2412.12861/) (2024)
- [4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos](https://mlsanity.com/paper/2506.08015/) (2025)
- [Generalizable Human Gaussians for Sparse View Synthesis](https://mlsanity.com/paper/2407.12777/) (2024)

## Abstract (arXiv)

Dynamic 3D hand reconstruction from egocentric videos is essential for next-generation computing platforms such as AR/VR and AI glasses. Despite its importance, most prior works focus either on multi-view 3D hand reconstruction or on 4D human body reconstruction. Egocentric 4D hand reconstruction remains difficult due to rapid hand and camera motion, hand-object and inter-hand interactions, and inherent ambiguity from single-view observations. To address these challenges, we introduce Hand-4DGS, a feed-forward framework for dynamic 4D hand reconstruction from egocentric videos. Our approach incorporates a mesh-guided representation for structural priors and temporal convolutions to model dynamic motion. We evaluate our framework on H2O and ARCTIC, two egocentric hand-object interaction datasets, and show improvements over baselines. Our model can efficiently adapt to unseen videos from datasets that are not included in training. In addition, image supervision through differentiable Gaussian rasterization provides an additional signal for appearance optimization and pose adjustment during training and test-time optimization, without ground-truth 3D hand pose annotations.