为辐射场建模细粒度不确定性，低成本且可优化。
Manifold Sampling for Differentiable Uncertainty in Radiance Fields
- 将不确定性视为参数空间的低维流形，支持高效采样
- 实现梯度可导的不确定性估计，用于优化视角选择
- 在最优视角规划任务中达到领先性能
辐射场是表示复杂场景外观的强大且流行的模型。然而，基于图像观测构建辐射场会引发歧义和不确定性。本文提出一种通用方法，可学习具有显式且细粒度不确定性估计的高斯辐射场，额外计算成本极低。核心观察是：不确定性可在辐射场参数空间中建模为低维流形，非常适合蒙特卡洛采样。重要的是，该不确定性具有可微性，允许通过梯度优化后续观测，以最优方式减少歧义。我们在下一最佳视角规划任务中展示了当前最优性能，包括高维光照规划，以实现最佳辐射场重光照质量。
原文摘要 · Abstract (English)
Radiance fields are powerful and, hence, popular models for representing the appearance of complex scenes. Yet, constructing them based on image observations gives rise to ambiguities and uncertainties. We propose a versatile approach for learning Gaussian radiance fields with explicit and fine-grained uncertainty estimates that impose only little additional cost compared to uncertainty-agnostic training. Our key observation is that uncertainties can be modeled as a low-dimensional manifold in the space of radiance field parameters that is highly amenable to Monte Carlo sampling. Importantly, our uncertainties are differentiable and, thus, allow for gradient-based optimization of subsequent captures that optimally reduce ambiguities. We demonstrate state-of-the-art performance on next-best-view planning tasks, including high-dimensional illumination planning for optimal radiance field relighting quality.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。