Newest papers

AnyGameRenderer: Entity-Consistent Generative Rendering Across Games and an Entity-Level Benchmark

Ruicong Liu, Liangyang Ouyang, Fengbo Lan, Zhixiang Wang, Kaipeng Zhang · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31466 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

Qualquer agente de codificação de dados controlado por agentes de desencadeamento de AI pode agora construir pequenos jogos jogáveis de dados em minutos, mas os resultados geralmente parecem arte de programação: bloqueio cinza, primitivas geométricas coloridas e blobs semânticos de tempo. Nós apresentamos o AnyGameRenderer, um gerador de vídeo-para-vídeo que transforma tais imagens em imagens de alta qualidade com personagens, detalhes de movimento e efeitos. Ao longo do tempo, ele mantém o layout, a câmera e a posição e o tempo de cada entidade intacto. Nosso AnyGameRenderer generaliza uma ampla gama de gêneros que os agentes construem, como defesa de torre, batalheiros automáticos, sobreviventes de topo, batalhas baseadas em turn-down, casos de

Machine translation (Meta M2M100); the English original follows.

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Rendering (computer graphics), Artificial intelligence, Hallucinating, CLIPS, Generative grammar

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange