跳到正文

认识 Déjà View:这是一种能将从不同角度拍摄的照片转换为 3D 几何结构和相机位置的模型。通过循环运行单个 Transformer 模块,这个拥有 117M 参数的模型在五项基准测试中,性能可媲美或超过规模大其最多 10 倍的模型,同时计算量相当或更低。研究人员可以调整循环次数,以适应计算预算。#NeurIPS2026 口头报告论文 + 代码:http://research.nvidia.com/labs/dvl/projects/dvlt

NVIDIA AI · X· @NVIDIAAI·· 5 天前

3496 次浏览 · 55 赞 · 11 转发 (收录时)

原文
谁
NVIDIA researchers
引文
Meet Déjà View, a model that turns photos taken from different angles into 3D geometry and camera positions.

发生了什么

认识 Déjà View:这是一种能将从不同角度拍摄的照片转换为 3D 几何结构和相机位置的模型。 通过循环运行单个 Transformer 模块,这个拥有 117M 参数的模型在五项基准测试中,性能可媲美或超过规模大其最多 10 倍的模型,同时计算量相当或更低。研究人员可以调整循环次数,以适应计算预算。 #NeurIPS2026 口头报告论文 + 代码:research.nvidia.com/labs/dvl/…

接下来读什么

查看这件事的完整进展NVIDIA Researchers Introduce Déjà View for 3D Reconstruction from Photos
正文 · 中文版本尚未就绪(原文)

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: research.nvidia.com/labs/dvl/…

这件事到目前为止

NVIDIA researchers introduced Déjà View, a 117-million-parameter model that reconstructs 3D geometry and camera positions from photos taken at different angles. The researchers said it matched or outperformed models up to ten times larger on five benchmarks while using comparable or less compute. Déjà View loops a single transformer block, and researchers can adjust the number of loops to fit their compute budget. NVIDIA presented the work as a NeurIPS 2026 oral paper and shared its code.