恒定内存可微光线追踪
Constant-Memory Differentiable Light Tracing
浏览论文内容
中文总结 AI 辅助
针对光线追踪中PRB无法恒定内存扩展的问题，提出ResLRB和LRB-3-pass两种恒定内存反向模式方法，分别通过储层采样压缩连接和额外遍历累积伴随，实现可微光线追踪并验证其正确性。
中文摘要 AI 辅助
蒙特卡洛光传输的反向模式微分天真地需要存储一个计算图，其大小随路径长度增长，这使得它对于深度或高样本模拟不切实际。路径回放反向传播（PRB）通过从随机种子重建路径并执行恒定内存的反向重放，消除了视点路径追踪的这种内存复杂性。然而，该公式依赖于一对一像素的属性，该属性对于光线追踪不成立：单个光线路径可以贡献给许多像素，并且相应的逐顶点伴随量无法在重放期间从恒定大小的状态中恢复。我们证明，这种结构差异阻止了PRB在恒定内存中直接扩展到光线追踪，并且缓冲的两遍变体保持与路径长度线性增长的内存缩放。然后，我们引入了两种用于可微光线追踪的恒定内存反向模式公式。第一种，储层光线重放反向传播（ResLRB），使用加权储层采样将每条路径的传感器连接集合压缩为单个随机选择的代表，保留两遍结构，代价是梯度方差增加。第二种，LRB-3遍，引入了额外的遍历，在反向传播之前累积下游伴随贡献，保留所有连接并在期望上匹配朴素反向模式AD。两种方法都支持分离和附加公式，包括由几何扰动引起的传感器溅射位置的微分。我们对照朴素AD验证正确性，表征内存和运行时权衡，并演示完全由光线追踪驱动的镜面焦散逆渲染。
英文摘要
Reverse-mode differentiation of Monte Carlo light transport naively requires storing a computation graph whose size grows with path length, making it impractical for deep or high-sample simulations. Path Replay Backpropagation (PRB) eliminates this memory complexity for viewpoint path tracing by reconstructing paths from their random seeds and performing a constant-memory backward replay. However, this formulation relies on a one-path-one-pixel property that does not hold for light tracing: a single light path can contribute to many pixels, and the corresponding per-vertex adjoints cannot be recovered during replay from constant-size state. We demonstrate that this structural difference prevents a direct extension of PRB to light tracing in constant memory, and that buffered two-pass variants retain linear memory scaling with path length. We then introduce two constant-memory reverse-mode formulations for differentiable light tracing. The first, Reservoir Light Replay Backpropagation (ResLRB), compresses the set of per-path sensor connections into a single stochastically selected representative using weighted reservoir sampling, preserving a two-pass structure at the cost of increased gradient variance. The second, LRB-3-pass, introduces an additional traversal that accumulates downstream adjoint contributions prior to backpropagation, retaining all connections and matching naive reverse-mode AD in expectation. Both methods support detached and attached formulations, including differentiation of sensor splat positions induced by geometric perturbations. We validate correctness against naive AD, characterize memory and runtime trade-offs, and demonstrate inverse rendering of specular caustics driven entirely by light tracing.
发表机构
- Simon Fraser University（西蒙菲莎大学）
机构由 AI 辅助整理，请以论文原文为准。
