# 4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video

arXiv: https://arxiv.org/abs/2603.10125 · HTML: https://mlsanity.com/paper/2603.10125/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 61 references that are in the map.
- First posted on arXiv 10 Mar 2026.

## Builds on (most cited first, 30 of 50)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Point Transformer](https://mlsanity.com/paper/2011.00931/) (2020)
- [Nerfies: Deformable Neural Radiance Fields](https://mlsanity.com/paper/2011.12948/) (2020)
- [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [The 2017 DAVIS Challenge on Video Object Segmentation](https://mlsanity.com/paper/1704.00675/) (2017)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [CoTracker: It is Better to Track Together](https://mlsanity.com/paper/2307.07635/) (2023)
- [MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion](https://mlsanity.com/paper/2410.03825/) (2024)
- [Learning Category-Specific Mesh Reconstruction from Image Collections](https://mlsanity.com/paper/1803.07549/) (2018)
- [3D Menagerie: Modeling the 3D shape and pose of animals](https://mlsanity.com/paper/1611.07700/) (2016)
- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)
- [BANMo: Building Animatable 3D Neural Models from Many Casual Videos](https://mlsanity.com/paper/2112.12761/) (2021)
- [Tracking Everything Everywhere All at Once](https://mlsanity.com/paper/2306.05422/) (2023)
- [GART: Gaussian Articulated Template Models](https://mlsanity.com/paper/2311.16099/) (2023)
- [LASR: Learning Articulated Shape Reconstruction from a Monocular Video](https://mlsanity.com/paper/2105.02976/) (2021)
- [MagicPony: Learning Articulated 3D Animals in the Wild](https://mlsanity.com/paper/2211.12497/) (2022)
- [MV-Adapter: Multi-view Consistent Image Generation Made Easy](https://mlsanity.com/paper/2412.03632/) (2024)
- [Three-D Safari: Learning to Estimate Zebra Pose, Shape, and Texture from Images "In the Wild"](https://mlsanity.com/paper/1908.07201/) (2019)
- [TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos](https://mlsanity.com/paper/2403.17346/) (2024)
- [SAMURAI: Adapting Segment Anything Model for Zero-Shot Visual Tracking with Motion-Aware Memory](https://mlsanity.com/paper/2411.11922/) (2024)
- [St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World](https://mlsanity.com/paper/2504.13152/) (2025)
- [Creatures great and SMAL: Recovering the shape and motion of animals from video](https://mlsanity.com/paper/1811.05804/) (2018)
- [ViTPose++: Vision Transformer for Generic Body Pose Estimation](https://mlsanity.com/paper/2212.04246/) (2022)
- [DOVE: Learning Deformable 3D Objects by Watching Videos](https://mlsanity.com/paper/2107.10844/) (2021)

## Built on by (most cited first, 2 of 2)

- [SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild](https://mlsanity.com/paper/2605.07604/) (2026)
- [ORMA: Optimization-based Monocular 4D Reconstruction of Articulated Animals](https://mlsanity.com/paper/2609.37986/) (2026)

## Abstract (arXiv)

4D reconstruction of equine family (e.g. horses) from monocular video is important for animal welfare. Previous mainstream 4D animal reconstruction methods require joint optimization of motion and appearance over a whole video, which is time-consuming and sensitive to incomplete observation. In this work, we propose a novel framework called 4DEquine by disentangling the 4D reconstruction problem into two sub-problems: dynamic motion reconstruction and static appearance reconstruction. For motion, we introduce a simple yet effective spatio-temporal transformer with a post-optimization stage to regress smooth and pixel-aligned pose and shape sequences from video. For appearance, we design a novel feed-forward network that reconstructs a high-fidelity, animatable 3D Gaussian avatar from as few as a single image. To assist training, we create a large-scale synthetic motion dataset, VarenPoser, which features high-quality surface motions and diverse camera trajectories, as well as a synthetic appearance dataset, VarenTex, comprising realistic multi-view images generated through multi-view diffusion. While training only on synthetic datasets, 4DEquine achieves state-of-the-art performance on real-world APT36K and AiM datasets, demonstrating the superiority of 4DEquine and our new datasets for both geometry and appearance reconstruction. Comprehensive ablation studies validate the effectiveness of both the motion and appearance reconstruction network. Project page: https://luoxue-star.github.io/4DEquine_Project_Page/.