面向几何视角扩散模型的景观感知
Landscape-Awareness for Geometric View Diffusion Model
把 Zero123 类新视角扩散模型反用于相机位姿估计时，可用基于 score 的景观重塑（landscape reshaping）替代朴素 multi-start 采样，缓解对称/自相似导致的局部极小，从而提升收敛速度与样本效率；这一优化思路可直接迁移到任何以扩散先验做位姿/参数反演的视觉任务。
原文依据 we propose a score-based method that reshapes the optimization landscape to guide updates toward the ground-truth viewpoint
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论在稀疏视角条件下，尤其是双视角场景中，精确的相机视角估计仍然具有挑战性。近期方法借助 Zero123 等扩散模型，以相对视角为条件合成新视角，并在通过 MSE 损失优化将其改用于视角估计时展现出良好前景。然而，现有方法往往受困于包含大量局部极小的非凸损失景观，使其对初始化敏感，并依赖朴素的多起点策略。我们分析了这些优化挑战并可视化了失败案例，表明对称性与自相似性等几何歧义会将基于梯度的更新误导至错误视角。为解决这些局限，我们提出一种基于分数的方法，重塑优化景观以将更新引导至真实视角，随后使用以视角为条件的扩散模型进行精化阶段。实验表明，我们的方法改善了收敛性，减少了对暴力采样的依赖，并在更高样本效率下取得了有竞争力的精度。
英文原文摘要 1128 字符
Accurate camera viewpoint estimation under sparse-view conditions remains challenging, particularly in two-view scenarios. Recent approaches leverage diffusion models such as Zero123 to synthesize novel views conditioned on relative viewpoint, showing promising results when repurposed for viewpoint estimation via optimization with MSE loss. However, existing methods often suffer from non-convex loss landscape with numerous local minima, making them sensitive to initialization and reliant on naive multi-start strategies. We analyze these optimization challenges and visualize failure cases, showing that geometric ambiguities, such as symmetry and self-similarity, can mislead gradient-based updates toward incorrect viewpoints. To address these limitations, we propose a score-based method that reshapes the optimization landscape to guide updates toward the ground-truth viewpoint, followed by a refinement stage using a viewpoint-conditioned diffusion model. Experiments show that our method improves convergence, reduces reliance on brute-force sampling, and achieves competitive accuracy with higher sample-efficiency.