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。AI 中文总结
该研究提出ResLRB方法，通过随机图压缩实现恒定内存的反向模式可微光线追踪，仅保留每条光线路径的单个传感器连接，得到无偏梯度估计器，降低内存占用。
AI 中文摘要
我们提出了Reservoir Light Replay Backpropagation（ResLRB），这是一种反向模式可微光线追踪方法，其内存占用在路径长度和每条光线路径的传感器连接数量上均为恒定值。光线追踪器的朴素自动微分会记录一个计算图，该图会随每条路径上有效传感器连接的数量增长，因为通量可从每个散射顶点进行溅射；伴随路径重播消除了视角路径追踪对深度的类似依赖，但其非分支结构无法扩展到溅射情况。我们在原过程中通过流式加权水库随机保留每条光线路径的单个代表性传感器连接，以此压缩伴随图。伴随过程通过重放其伪随机数序列确定性地重建路径，且仅通过保留的连接进行反向传播，从而得到一个无偏梯度估计器，其峰值内存与对单个散射事件求导的内存相当。
英文摘要
We describe Reservoir Light Replay Backpropagation (ResLRB), a method for reverse-mode differentiable light tracing whose memory is constant in path length and in the number of sensor connections per light path. Naive automatic differentiation of a light tracer records a computation graph that grows with the number of valid sensor connections along each path, since flux can be splatted from every scattering vertex; adjoint path replay removes the analogous dependence on depth for viewpoint path tracing, but its non-branching structure does not extend to the splatting case. We compress the adjoint graph during the primal pass by stochastically retaining a single representative sensor connection per light path via a streaming weighted reservoir. The adjoint pass reconstructs the path deterministically by replaying its pseudorandom number sequence and backpropagates only through the retained connection, yielding an unbiased gradient estimator whose peak memory is that of differentiating a single scattering event.
Comments4 pages. SIGGRAPH Asia 2026 Technical Communications
Journal refSIGGRAPH Asia 2026 Technical Communications (SA Technical Communications '26), Kuala Lumpur, Malaysia
