LiteVoxel让体素渲染更省显存，同时保留低频细节。
LiteVoxel: Low-memory Intelligent Thresholding for Efficient Voxel Rasterization
- 用动态阈值和优先级细分替代固定规则，自适应控制体素生长
- 在6个场景上降低40%-60%峰值显存，保持与强基线相当的画质
- 适合需要低显存、高稳定性的三维重建任务
稀疏体素光栅化是优化驱动场景重建的快速可微方法，但常导致低频内容欠拟合、依赖脆弱的剪枝启发式，并引发显存膨胀。我们提出LiteVoxel，一种自调优训练流程，使SV光栅化更稳定且更轻量。通过逆Sobel重加权与中期γ阶梯调整，损失函数关注低频区域，在几何稳定后才分配梯度预算。自适应剪枝将固定阈值替换为基于最大混合权重的深度分位数逻辑，由EMA滞环保护稳定；并通过射线足迹引导的优先级细分，在明确增长预算下优化结构。在Mip-NeRF 360（6场景）和Tanks & Temples（3场景）上的消融实验与全系统结果表明，该方法有效缓解了低频区域误差与边界不稳定性，同时保持与强基线相当的PSNR/SSIM、训练时间与帧率。关键在于，LiteVoxel将峰值显存降低约40%-60%，并保留了先前方案遗漏的低频细节，实现无需牺牲感知质量的可预测、高效训练。
原文摘要 · Abstract (English)
Sparse-voxel rasterization is a fast, differentiable alternative for optimization-based scene reconstruction, but it tends to underfit low-frequency content, depends on brittle pruning heuristics, and can overgrow in ways that inflate VRAM. We introduce LiteVoxel, a self-tuning training pipeline that makes SV rasterization both steadier and lighter. Our loss is made low-frequency aware via an inverse-Sobel reweighting with a mid-training gamma-ramp, shifting gradient budget to flat regions only after geometry stabilize. Adaptation replaces fixed thresholds with a depth-quantile pruning logic on maximum blending weight, stabilized by EMA-hysteresis guards and refines structure through ray-footprint-based, priority-driven subdivision under an explicit growth budget. Ablations and full-system results across Mip-NeRF 360 (6scenes) and Tanks & Temples (3scenes) datasets show mitigation of errors in low-frequency regions and boundary instability while keeping PSNR/SSIM, training time, and FPS comparable to a strong SVRaster pipeline. Crucially, LiteVoxel reduces peak VRAM by ~40%-60% and preserves low-frequency detail that prior setups miss, enabling more predictable, memory-efficient training without sacrificing perceptual 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。