JiahaoPlus/EvoWorld
EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory
This project helps generate realistic, consistent future video frames from a single panoramic image and camera movement data. It takes an initial panoramic view and a sequence of desired camera positions as input, then produces a video that accurately reflects those movements in a simulated 3D environment. This is useful for researchers and creators working on virtual reality, game development, or realistic simulation.
Use this if you need to create extended, highly consistent video sequences from a single starting panoramic image, particularly for virtual environments where camera motion is predefined.
Not ideal if you're looking to generate videos from standard, non-panoramic images or if your primary goal is artistic stylization rather than 3D consistency.
Stars
61
Forks
1
Language
Python
License
MIT
Category
Last pushed
Jan 13, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/JiahaoPlus/EvoWorld"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ZiYang-xie/WorldGen
🌍 WorldGen - Generate Any 3D Scene in Seconds
aioz-ai/AIOZ-GDANCE
AIOZ-GDANCE: a large-scale dataset & baseline for music-driven group dance generation. (CVPR 2023)
worldbench/WorldLens
[CVPR 2026] WorldLens: Full-Spectrum Evaluations of Driving World Models in Real World
Kobaayyy/Awesome-CVPR2026-CVPR2025-ICCV2025-CVPR2024-ECCV2024-AIGC
A Collection of Papers and Codes for CVPR2026/CVPR2025/ICCV2025/CVPR2024/ECCV2024 AIGC
nv-tlabs/XCube
[CVPR 2024 Highlight] XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies