EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
- URL: http://arxiv.org/abs/2510.01183v1
- Date: Wed, 01 Oct 2025 17:59:38 GMT
- Title: EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
- Authors: Jiahao Wang, Luoxin Ye, TaiMing Lu, Junfei Xiao, Jiahan Zhang, Yuxiang Guo, Xijun Liu, Rama Chellappa, Cheng Peng, Alan Yuille, Jieneng Chen,
- Abstract summary: EvoWorld bridges panoramic video generation with evolving 3D memory to enable spatially consistent long-horizon exploration.<n>Unlike prior state-of-the-arts that synthesize videos only, our key insight lies in exploiting this evolving 3D reconstruction as explicit spatial guidance.<n>To evaluate long-range exploration capabilities, we introduce the first comprehensive benchmark spanning synthetic outdoor environments, Habitat indoor scenes, and challenging real-world scenarios.
- Score: 40.346684158976494
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Humans possess a remarkable ability to mentally explore and replay 3D environments they have previously experienced. Inspired by this mental process, we present EvoWorld: a world model that bridges panoramic video generation with evolving 3D memory to enable spatially consistent long-horizon exploration. Given a single panoramic image as input, EvoWorld first generates future video frames by leveraging a video generator with fine-grained view control, then evolves the scene's 3D reconstruction using a feedforward plug-and-play transformer, and finally synthesizes futures by conditioning on geometric reprojections from this evolving explicit 3D memory. Unlike prior state-of-the-arts that synthesize videos only, our key insight lies in exploiting this evolving 3D reconstruction as explicit spatial guidance for the video generation process, projecting the reconstructed geometry onto target viewpoints to provide rich spatial cues that significantly enhance both visual realism and geometric consistency. To evaluate long-range exploration capabilities, we introduce the first comprehensive benchmark spanning synthetic outdoor environments, Habitat indoor scenes, and challenging real-world scenarios, with particular emphasis on loop-closure detection and spatial coherence over extended trajectories. Extensive experiments demonstrate that our evolving 3D memory substantially improves visual fidelity and maintains spatial scene coherence compared to existing approaches, representing a significant advance toward long-horizon spatially consistent world modeling.
Related papers
- Beyond Pixel Histories: World Models with Persistent 3D State [50.4601060508243]
PERSIST is a new paradigm of world model which simulates the evolution of a latent 3D scene.<n>We show substantial improvements in spatial memory, 3D consistency, and long-horizon stability over existing methods.
arXiv Detail & Related papers (2026-03-03T19:58:31Z) - WorldStereo: Bridging Camera-Guided Video Generation and Scene Reconstruction via 3D Geometric Memories [36.79437857022868]
WorldStereo is a novel framework that bridges camera-guided video generation and 3D reconstruction.<n>We show that WorldStereo acts as a powerful world model, tackling diverse scene generation tasks with high-fidelity 3D results.
arXiv Detail & Related papers (2026-03-02T16:36:56Z) - WorldGrow: Generating Infinite 3D World [75.81531067447203]
We tackle the challenge of generating the infinitely extendable 3D world -- large, continuous environments with coherent geometry and realistic appearance.<n>We propose WorldGrow, a hierarchical framework for unbounded 3D scene synthesis.<n>Our method features three core components: (1) a data curation pipeline that extracts high-quality scene blocks for training, making the 3D structured latent representations suitable for scene generation; (2) a 3D block inpainting mechanism that enables context-aware scene extension; and (3) a coarse-to-fine generation strategy that ensures both global layout plausibility and local geometric/textural fidelity.
arXiv Detail & Related papers (2025-10-24T17:39:52Z) - PanoWorld-X: Generating Explorable Panoramic Worlds via Sphere-Aware Video Diffusion [87.13016347332943]
PanoWorld-X is a novel framework for high-fidelity and controllable panoramic video generation with diverse camera trajectories.<n>Our experiments demonstrate superior performance in various aspects, including motion range, control precision, and visual quality.
arXiv Detail & Related papers (2025-09-29T16:22:00Z) - FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction [13.098585993121722]
We present FantasyWorld, a geometry-enhanced framework that augments frozen video foundation models with a trainable geometric branch.<n>Our approach introduces cross-branch supervision, where geometry cues guide video generation and video priors regularize 3D prediction.<n>Experiments show that FantasyWorld effectively bridges video imagination and 3D perception, outperforming recent geometry-consistent baselines in multi-view coherence and style consistency.
arXiv Detail & Related papers (2025-09-25T22:24:23Z) - Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation [66.95956271144982]
We present Voyager, a novel video diffusion framework that generates world-consistent 3D point-cloud sequences from a single image.<n>Unlike existing approaches, Voyager achieves end-to-end scene generation and reconstruction with inherent consistency across frames.
arXiv Detail & Related papers (2025-06-04T17:59:04Z) - WorldExplorer: Towards Generating Fully Navigable 3D Scenes [48.16064304951891]
WorldExplorer builds fully navigable 3D scenes with consistent visual quality across a wide range of viewpoints.<n>We generate multiple videos along short, pre-defined trajectories, that explore the scene in depth.<n>Our novel scene memory conditions each video on the most relevant prior views, while a collision-detection mechanism prevents degenerate results.
arXiv Detail & Related papers (2025-06-02T15:41:31Z) - SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations [44.53106180688135]
This work takes on the challenge of reconstructing 3D scenes from sparse or single-view inputs.<n>We introduce SpatialCrafter, a framework that leverages the rich knowledge in video diffusion models to generate plausible additional observations.<n>Through a trainable camera encoder and an epipolar attention mechanism for explicit geometric constraints, we achieve precise camera control and 3D consistency.
arXiv Detail & Related papers (2025-05-17T13:05:13Z) - Learning 3D Persistent Embodied World Models [84.40585374179037]
We introduce a new persistent embodied world model with an explicit memory of previously generated content.<n>During generation time, our video diffusion model predicts RGB-D video of the future observations of the agent.<n>This generation is then aggregated into a persistent 3D map of the environment.
arXiv Detail & Related papers (2025-05-05T17:59:17Z) - ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis [63.169364481672915]
We propose textbfViewCrafter, a novel method for synthesizing high-fidelity novel views of generic scenes from single or sparse images.
Our method takes advantage of the powerful generation capabilities of video diffusion model and the coarse 3D clues offered by point-based representation to generate high-quality video frames.
arXiv Detail & Related papers (2024-09-03T16:53:19Z)
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.