用动态步长优化3D重建，单图或多图都能高效生成高质量点云。
Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates
- 通过前向曲率匹配法自动计算最优更新步长，无需手动调参。
- 在ShapeNet和CO3D上达成更高精度，比现有方法更少计算量（更低NFE）。
- 支持单图、多图及不同输入模态，无需重新训练，适合实际部署。
从图像中重建高质量点云仍是计算机视觉的挑战。现有基于生成模型的方法，尤其是直接学习后验的扩散模型，存在灵活性差的问题：训练需依赖条件信号，仅支持固定数量输入视图，且针对不同测量需完整重训练。近期方法尝试结合先验模型与似然更新以缓解此问题，但依赖启发式固定步长，导致收敛慢、重建质量不佳。本文提出将新型前向曲率匹配（Forward Curvature-Matching, FCM）更新方法与扩散采样结合，利用前向自动微分和有限差分曲率估计，动态确定最优步长，实现似然更新的精准优化。该方法可高保真地实现单视图与多视图输入的重建，并通过简单算子替换支持多种输入模态，且无需重训练。在ShapeNet和CO3D数据集上的实验表明，本方法在匹配或更低的NFE下达到更优重建质量，F-score更高，CD与EMD更低，验证了其效率与适应性。代码已开源：https://github.com/Seunghyeok0715/FCM。
原文摘要 · Abstract (English)
Reconstructing high-quality point clouds from images remains challenging in computer vision. Existing generative-model-based approaches, particularly diffusion-model approaches that directly learn the posterior, may suffer from inflexibility -- they require conditioning signals during training, support only a fixed number of input views, and need complete retraining for different measurements. Recent diffusion-based methods have attempted to address this by combining prior models with likelihood updates, but they rely on heuristic fixed step sizes for the likelihood update that lead to slow convergence and suboptimal reconstruction quality. We advance this line of approach by integrating our novel Forward Curvature-Matching (FCM) update method with diffusion sampling. Our method dynamically determines optimal step sizes using only forward automatic differentiation and finite-difference curvature estimates, enabling precise optimization of the likelihood update. This formulation enables high-fidelity reconstruction from both single-view and multi-view inputs, and supports various input modalities through simple operator substitution -- all without retraining. Experiments on ShapeNet and CO3D datasets demonstrate that our method achieves superior reconstruction quality at matched or lower NFEs, yielding higher F-score and lower CD and EMD, validating its efficiency and adaptability for practical applications. Code is available at https://github.com/Seunghyeok0715/FCM
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。