4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video
- URL: http://arxiv.org/abs/2603.10125v1
- Date: Tue, 10 Mar 2026 18:01:10 GMT
- Title: 4DEquine: Disentangling Motion and Appearance for 4D Equine Reconstruction from Monocular Video
- Abstract summary: We propose a novel framework called 4DEquine to disentangling the 4D reconstruction problem into two sub-problems: dynamic motion reconstruction and static appearance reconstruction.<n>For motion, we introduce a simple yet effective yet effective transformer with a post-optimization stage to regress smooth and pixel-aligned pose and shape sequences from video.<n>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.
- Score: 40.23548336607091
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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/.
Related papers
- World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video [62.16750462940772]
We present World from Motion, a method for generating freely renderable dynamic 3D Gaussian representations from monocular videos.<n>Our approach conditions a video model on dense, pixel-aligned renderings that encode appearance, geometry, and 3D scene motion.<n>At test time, we distill the model's generations back into a single consistent, high-quality dynamic 3DGS, improving both novel-view synthesis and the underlying 3D motion.
arXiv Detail & Related papers (2026-07-01T17:41:00Z) - ArtHOI: Articulated Human-Object Interaction Synthesis by 4D Reconstruction from Video Priors [51.06020148149403]
We introduce ArtHOI, the first zero-shot framework for articulated human-object interaction synthesis via 4D reconstruction from video priors.<n>ArtHOI bridges video-based generation and geometry-aware reconstruction, producing interactions that are both semantically aligned and physically grounded.
arXiv Detail & Related papers (2026-03-04T17:58:04Z) - Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis [53.48281548500864]
Motion 3-to-4 is a feed-forward framework for synthesising high-quality 4D dynamic objects from a single monocular video.<n>Our model learns a compact motion latent representation and predicts per-frame trajectories to recover complete robustness, temporally coherent geometry.
arXiv Detail & Related papers (2026-01-20T18:59:48Z) - Mesh4D: 4D Mesh Reconstruction and Tracking from Monocular Video [81.44600627066747]
Mesh4D is a feed-forward model for monocular 4D mesh reconstruction.<n>Our key contribution is a compact latent space that encodes the entire animation sequence in a single pass.<n>We evaluate Mesh4D on reconstruction and view novel benchmarks, outperforming prior methods in recovering accurate 3D shape and deformation.
arXiv Detail & Related papers (2026-01-08T18:59:56Z) - Web-Scale Collection of Video Data for 4D Animal Reconstruction [26.179284343904897]
We introduce an automated pipeline that mines YouTube videos and processes them into object-centric clips.<n>Using this pipeline, we amass 30K videos (2M frames)--an order of magnitude more than prior works.<n>We present Animal-in-Motion, a benchmark of 230 manually filtered sequences with 11K frames showcasing clean, diverse animal motions.
arXiv Detail & Related papers (2025-11-03T02:40:06Z) - Diff4Splat: Controllable 4D Scene Generation with Latent Dynamic Reconstruction Models [79.06910348413861]
We introduce Diff4Splat, a feed-forward method that synthesizes controllable and explicit 4D scenes from a single image.<n>Given a single input image, a camera trajectory, and an optional text prompt, Diff4Splat directly predicts a deformable 3D Gaussian field that encodes appearance, geometry, and motion.
arXiv Detail & Related papers (2025-11-01T11:16:25Z) - Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video [56.781766315691854]
We introduce textbfRestage4D, a geometry-preserving pipeline for video-conditioned 4D restaging.<n>We validate Restage4D on DAVIS and PointOdyssey, demonstrating improved geometry consistency, motion quality, and 3D tracking performance.
arXiv Detail & Related papers (2025-08-08T21:31:51Z) - MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds [27.802537831023347]
We introduce 4D Motion Scaffolds (MoSca), a modern 4D reconstruction system designed to reconstruct and synthesize novel views of dynamic scenes from monocular videos captured casually in the wild.<n> Experiments demonstrate state-of-the-art performance on dynamic rendering benchmarks and its effectiveness on real videos.
arXiv Detail & Related papers (2024-05-27T17:59:07Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.