OuroWorld is a mask‑free framework that transforms any static 3D Gaussian Splatting scene into a 3D cinemagraph, producing dynamic scenes with vivid, diverse motion that loop seamlessly from any viewpoint. It uses a vision‑language model to infer plausible dynamics and a video model to synthesize a reference video, which is then lifted and completed into multi‑view videos. The method introduces an Inconsistency‑Robust Periodic 4DGS with a Fourier‑series deformation field for guaranteed looping and a Grounded Drift Field to handle cross‑view inconsistencies, enabling general deformation, object motion, and illumination change beyond fluid‑like motion. Evaluation on 39 scenes shows OuroWorld outperforms baselines and wins 70.8%–99.0% of user‑study comparisons.
arXiv:2610.02160v1 Announce Type: new Abstract: Precise control over camera and object motion is essential for professional video production. Existing methods control objects only coarsely, through i...
arXiv:2607. 01202v1 Announce Type: cross Abstract: We present World from Motion, a method for generating freely renderable dynamic 3D Gaussian representations from monocular videos.
Novel view rendering of large and complex reconstructed scenes is becoming increasingly photorealistic. However, most reconstructions remain static and lack the ambient motion that makes environments immersive.
arXiv:2608. 19556v1 Announce Type: cross Abstract: Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry and dynamics of a coherent world: long rollouts accumulate geometric drift and degrade into static or unnatural motion.
Streaming autoregressive diffusion models enable real-time, long-horizon video generation, but their training objectives optimize local frame prediction rather than the geometry and dynamics of a coherent world: long rollouts accumulate geometric drift and degrade into static or unnatural motion. Recent bidirectional approaches address this problem using rewards signals built upon 3D Gaussian-Splatting reconstruction.
Forge4D is a feed‑forward model that reconstructs temporally aligned 4D human representations from uncalibrated sparse‑view videos, enabling both novel view and novel time synthesis. It achieves this by jointly streaming 3D Gaussian reconstruction with dense motion prediction, using learnable state tokens for temporal consistency and a self‑supervised retargeting loss for motion prediction. Extensive experiments confirm its effectiveness on in‑domain and out‑of‑domain datasets.
arXiv:2609.14462v1 Announce Type: new Abstract: Interactive video world models must maintain broad scene context under camera motion while producing high-fidelity observations with low latency. Exist...
arXiv:2609.36940v1 Announce Type: new Abstract: Accurate dynamic scene reconstruction is important for robotic perception, where temporally consistent representations of dynamic environments are esse...
arXiv:2609.01059v1 Announce Type: new Abstract: As Vision-Language Models (VLMs) tackle dynamic 3D spatial reasoning, ego-motion perception becomes essential to resolve monocular scale ambiguity. How...
arXiv:2610.04606v2 Announce Type: replace Abstract: We present a 4D Gaussian Splatting framework for the Sparse-View Track of the SIGGRAPH Asia 2026 Volumetric Video Challenge, which requires dynamic...
arXiv:2608.23549v1 Announce Type: new Abstract: Rendering views using 3D scene representations such as Gaussian Splatting (3DGS), Neural Radiance Fields (NeRF), meshes, or even point clouds produces...
arXiv:2609.13262v1 Announce Type: new Abstract: 3D Gaussian Splatting achieves photorealistic reconstruction within training view distribution, yet it degrades on out-of-distribution novel views, exh...