Guian Fang, Shengju Qian, Dongyue Lu, Junchao Huang, Lutao Jiang, Xin Wang, Yiren Song, Li Jiang · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28630 · open-access PDF
Mesin permainan dan agen pengkodean dapat menentukan tata letak, gerakan, dan kamera dari sebuah adegan, namun mengubah struktur kasar seperti itu menjadi video yang realistis membutuhkan render yang mengikuti struktur dan menyelesaikan penampilan yang meninggalkan terbuka. render yang ada terikat dengan representasi dari satu mesin, membutuhkan puluhan langkah denoising atau distilasi mahal sendiri, dan belajar dari kondisi yang tidak sesuai dengan video target mereka.
Machine translation (Meta M2M100); the English original follows.
Game engines and coding agents can specify the layout, motion, and camera of a scene, yet turning such coarse structure into realistic video requires a renderer that follows the structure and completes the appearance it leaves open. Existing renderers are tied to the representation of one engine, need tens of denoising steps or a costly distillation of their own, and learn from conditions that are not aligned with their target videos. We present SolarRenderer, a structure-conditioned video renderer that adapts a frozen MiniMax-H3 33B backbone with two lightweight LoRAs. Structural videos enter
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28630, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange