Tong Zhao, Zhiyuan Han, Lin Chen, Bowen Xie, Yunxi Qiao, Bohan Li, Weiqing Xiao, Gen Li, Shu Han, Xuyang Dai, Cheng Bi, Hao Zhao, Chaojian Li · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.26585 · cited by 0 works (OpenAlex) · open-access PDF
وتتطلب إنشاء بيئات القيادة المرتبطة بتنفيذ المراحل المستقبلية التي يمكن التحكم فيها وتشغيلها بشكل واضح من وجهات نظر مختلفة، إلا أن الأساليب الحالية لا تزال تتمكن من استرداد السيناريوهات المفصلة من أفلام RGB التي تم إنشاؤها من خلال تحسين كل سلسلة. لتغلب هذه القيود، ونحن نقدم Drive2Gauss، وهي إطار إعادة التدوير الذي يستخدم إعادة التدوير لتوليد الأسئلة التي تم إنشاؤها معًا من قبل RGB، والغبار المرتبطة بـ 3D، والهبوط الديناميكي إلى السيناريوهات 4D Gaussian الديناميكية. يوفر إعادة التدوير الفوتوغرافي الفوتوغرافي ثلاث طرق إعادة التدوير من صور
Machine translation (Meta M2M100); the English original follows.
Generating reusable driving environments requires both controllable future observations and an explicit representation that supports rendering from different viewpoints, yet existing methods still recover explicit scenes from generated RGB videos through optimization for each sequence. To overcome these limitations, we present Drive2Gauss, a feedforward framework that converts jointly generated RGB, metric depth, and dynamic flow into dynamic 4D Gaussian scenes. A Multimodal Video Generator predicts the three modalities from reference multiview images and future control signals. Furthermore, we introduce a Gaussian Query Decoder that uses depth to initialize sparse 3D queries and flow to associate the queries across time, and integrates appearance information through spatiotemporal feature aggregation and iterative query refinement. The reconstruction stage operates in a single feedforward pass without optimization for each scene. Extensive results on nuScenes demonstrate that our approach attains an FID of 6.38 and an FVD of 12.43 for future RGB generation, a PSNR of 29.91 dB when reconstructing its generated observations, and supports both direct rendering under lateral camera shifts and downstream video fixing. Code and more visualizations are available at https://zttt04. github.io/Drive2Gauss_page/.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Artificial intelligence, Rendering (computer graphics), Computer vision, Feed forward, RGB color model
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26585, 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