HuggingFace Daily Papers·· 1 天前
AnyGameRenderer：跨游戏的实体一致生成式渲染与实体级基准
AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark
AI 导读
AI 编程智能体能快速做出小游戏，但画面多为灰色块和几何图形。AnyGameRenderer 是视频到视频的生成式渲染器，通过 LoRA 微调 33B 的 MiniMax-H3 ref2va，把这类画面转成高质量视觉，同时保持布局、相机和每个实体的位置与时间不变。
正文 · 原文
Abstract:AI coding agents can now build small playable games in minutes, but the results usually look like programmer art: gray blockouts, colored geometric primitives, and flat semantic blobs. We present AnyGameRenderer, a video-to-video generative renderer that turns such footage into high-quality visuals with characters, motion detail, and effects. Throughout, it keeps the layout, camera, and every entity's position and timing intact.
Our AnyGameRenderer generalizes across a wide range of genres that agents build, such as tower defense, auto-battlers, top-down survivors, turn-based battles, kart racing, and crowd runners.
AnyGameRenderer takes plain video as its game-state input, with no complex representations such as engine G-buffers, per-object class labels, or low-poly proxies. Gray blockouts, colored primitives, semantic maps, and wireframes all work as input.
It also preserves entity correspondence: group counts stay correct, and entities appear and disappear on the right frame.
We implement AnyGameRenderer by LoRA fine-tuning MiniMax-H3 ref2va, a 33B reference-video-conditioned video generation model. Training uses $\sim$10k paired clips from three sources: (i) multi-stream rendering data from 38 agent-made games exported from GEAR, an AI game-creation tool; (ii) two-stream rendering data from Unreal Engine, with programmatically controlled crowds, count changes, and entity scales; and (iii) real gameplay recordings, with pairs reconstructed via 3D-box detection.
To evaluate the entity correspondence, we propose an entity-level benchmark of 59 held-out cases with 753 entities, scored against ground-truth boxes. Compared with the base model, AnyGameRenderer better preserves entity correspondence: temporal match rises from 50.9\% to 62.9\%, missed count changes fall from 34.7\% to 21.3\%, and fewer entities are hallucinated or left unrendered.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2610.31466 [cs.CV] |
| (or arXiv:2610.31466v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31466 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ruicong Liu [view email]
[v1]
Thu, 22 Oct 2026 15:58:39 UTC (6,583 KB)
来源：HuggingFace Daily Papers · arxiv.org