NVIDIA 发布并开源研究模型 Déjà View,可将不同角度拍摄的照片还原为 3D 几何与相机位姿。该模型仅 117M 参数,通过循环单个 Transformer 块,在五项基准上匹配或超过大至 10 倍的模型,且算力相当或更少,研究者可按算力预算调整循环次数。该工作为 NeurIPS2026 oral 论文,代码已公开。
Déjà vu
在第一次经历某个瞬间时,却仿佛已经拥有了关于这一瞬间的回忆。
在漩涡中的 NVIDIA 发布并开源了 Déjà View 的研究工作,仅 117M 参数,小而美而强大。
若干时间后,当你再次看见 Nvidia 的或许已经完全改变的标志和产品,它的气味和气质,与你曾经深深喜爱的东西,十分相似。
或许是因为曾经参与制造这种感觉的人非常伟大,这种感觉,更加难以忘掉。
【引用 @NVIDIAAI】Meet Déjà View, a model that turns photos taken from different angles into 3D geometry and camera positions.
By looping a single transformer block, this 117M-parameter model matches or outperforms models up to 10x larger across five benchmarks, using comparable or less compute. Researchers can dial the number of loops to fit their compute budget.
#NeurIPS2026 oral paper + code: http://research.nvidia.com/labs/dvl/projects/dvlt
Meet Déjà View, a model that turns photos taken from different angles into 3D geometry and camera positions. By looping a single transformer block, this 117M-parameter model matches or outperforms models up to 10x larger across five benchmarks, using comparable or less compute. Researchers can dial the number of loops to fit their compute budget. #NeurIPS2026 oral paper + code: http://research.nvidia.com/labs/dvl/projects/dvlt在 X 查看被引用的帖子
来源:Dongxi 东锡 NLP · x.com