在测试时利用先验学习三维重建
Learning 3D Reconstruction with Priors in Test Time
把相机位姿、内参、深度等先验转成推理时的惩罚项，配合多视图光度/几何一致性自监督目标，在冻结的 image-only 多视图 Transformer 上做测试时约束优化，可直接复用于点图估计、位姿估计等 3D 任务的后处理式性能提升。
原文依据 we cast them as constraints on the predictions and optimize the network at inference time
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出一种面向多视图 Transformer（MVT）的测试时框架，通过引入先验（如相机位姿、内参与深度）来提升三维任务性能，且无需重新训练或修改预训练的纯图像网络。我们并未将先验输入到网络架构中，而是将其视为对预测结果的约束，并在推理阶段对网络进行优化。优化损失由自监督目标与先验惩罚项构成。自监督目标刻画多视图预测之间的一致性，通过计算由其他视角渲染得到的图像与各视角自身之间的光度损失或几何损失来实现。任何可用的先验都被转换为对应输出模态上的惩罚项。在一系列三维视觉基准（包括点图估计与相机位姿估计）上，本方法相较基础 MVT 均能大幅且稳定地提升性能。在 ETH3D、7-Scenes 与 NRGBD 数据集上，本方法相较纯图像基础模型将点图距离误差降低一半以上。本方法还优于经重新训练的、具备先验感知的前馈方法，表明测试时约束优化（TCO）框架在将先验引入三维视觉任务方面是有效的。代码见 https://github.com/cvlab-stonybrook/TCO。
英文原文摘要 1349 字符
We introduce a test-time framework for multiview Transformers (MVTs) that incorporates priors (e.g., camera poses, intrinsics, and depth) to improve 3D tasks without retraining or modifying pre-trained image-only networks. Rather than feeding priors into the architecture, we cast them as constraints on the predictions and optimize the network at inference time. The optimization loss consists of a self-supervised objective and prior penalty terms. The self-supervised objective captures the compatibility among multi-view predictions and is implemented using photometric or geometric loss between renderings from other views and each view itself. Any available priors are converted into penalty terms on the corresponding output modalities. Across a series of 3D vision benchmarks, including point map estimation and camera pose estimation, our method consistently improves performance over base MVTs by a large margin. On the ETH3D, 7-Scenes, and NRGBD datasets, our method reduces the point-map distance error by more than half compared with the base image-only models. Our method also outperforms retrained prior-aware feed-forward methods, demonstrating the effectiveness of our test-time constrained optimization (TCO) framework for incorporating priors into 3D vision tasks. The code is available at https://github.com/cvlab-stonybrook/TCO.