ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914415334391808 |
|---|---|
| author | Yuan, Jinyan Yang, Bangbang Wang, Keke Pan, Panwang Ma, Lin Zhang, Xuehai Liu, Xiao Cui, Zhaopeng Ma, Yuewen |
| author_facet | Yuan, Jinyan Yang, Bangbang Wang, Keke Pan, Panwang Ma, Lin Zhang, Xuehai Liu, Xiao Cui, Zhaopeng Ma, Yuewen |
| contents | Automating immersive VR scene creation remains a primary research challenge. Existing methods typically rely on complex geometry with post-simplification, resulting in inefficient pipelines or limited realism. In this paper, we introduce ImmerseGen, a novel agent-guided framework for compact and photorealistic world generation that decouples realism from exhaustive geometric modeling. ImmerseGen represents scenes as hierarchical compositions of lightweight geometric proxies with synthesized RGBA textures, facilitating real-time rendering on mobile VR headsets. We propose terrain-conditioned texturing for base world generation, combined with context-aware texturing for scenery, to produce diverse and visually coherent worlds. VLM-based agents employ semantic grid-based analysis for precise asset placement and enrich scenes with multimodal enhancements such as visual dynamics and ambient sound. Experiments and real-time VR applications demonstrate that ImmerseGen achieves superior photorealism, spatial coherence, and rendering efficiency compared to existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_14315 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies Yuan, Jinyan Yang, Bangbang Wang, Keke Pan, Panwang Ma, Lin Zhang, Xuehai Liu, Xiao Cui, Zhaopeng Ma, Yuewen Graphics Computer Vision and Pattern Recognition Automating immersive VR scene creation remains a primary research challenge. Existing methods typically rely on complex geometry with post-simplification, resulting in inefficient pipelines or limited realism. In this paper, we introduce ImmerseGen, a novel agent-guided framework for compact and photorealistic world generation that decouples realism from exhaustive geometric modeling. ImmerseGen represents scenes as hierarchical compositions of lightweight geometric proxies with synthesized RGBA textures, facilitating real-time rendering on mobile VR headsets. We propose terrain-conditioned texturing for base world generation, combined with context-aware texturing for scenery, to produce diverse and visually coherent worlds. VLM-based agents employ semantic grid-based analysis for precise asset placement and enrich scenes with multimodal enhancements such as visual dynamics and ambient sound. Experiments and real-time VR applications demonstrate that ImmerseGen achieves superior photorealism, spatial coherence, and rendering efficiency compared to existing methods. |
| title | ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.14315 |