让视频3D重建在任意长序列下保持稳定，且内存计算不变。
OVGGT: O(1) Constant-Cost Streaming Visual Geometry Transformer
- 用自选择缓存压缩键值对，配合动态锚点保护关键特征
- 处理超长视频时内存与计算量恒定，不随帧数增长
- 适合需要长时间连续3D重建的场景，如自动驾驶
从流式视频重建3D几何结构需在资源受限下持续推理。现有几何基础模型虽通过全连接注意力实现高质量重建，但其二次复杂度限制了仅能处理短序列。因果注意力方法如StreamVGGT可单次遍历处理，但会积累不断增长的键值缓存，在数百帧后耗尽GPU显存，违背了长时推理的初衷。本文提出OVGGT，一种无需训练的框架，使内存与计算量恒定，不受序列长度影响。该方法结合自选择缓存机制，利用前馈网络残差大小压缩键值缓存，兼容FlashAttention；以及动态锚点保护，防止关键坐标特征被剔除，有效抑制长轨迹下的几何漂移。在室内、室外及超长序列基准测试中，OVGGT可在固定显存范围内处理任意长度视频，并达到当前最优的3D几何精度。
原文摘要 · Abstract (English)
Reconstructing 3D geometry from streaming video requires continuous inference under bounded resources. Recent geometric foundation models achieve impressive reconstruction quality through all-to-all attention, yet their quadratic cost confines them to short, offline sequences. Causal-attention variants such as StreamVGGT enable single-pass streaming but accumulate an ever-growing KV cache, exhausting GPU memory within hundreds of frames and precluding the long-horizon deployment that motivates streaming inference in the first place. We present OVGGT, a training-free framework that bounds both memory and compute to a fixed budget regardless of sequence length. Our approach combines Self-Selective Caching, which leverages FFN residual magnitudes to compress the KV cache while remaining fully compatible with FlashAttention, with Dynamic Anchor Protection, which shields coordinate-critical tokens from eviction to suppress geometric drift over extended trajectories. Extensive experiments on indoor, outdoor, and ultra-long sequence benchmarks demonstrate that OVGGT processes arbitrarily long videos within a constant VRAM envelope while achieving state-of-the-art 3D geometric accuracy. Project page: https://vaisr.github.io/OVGGT/ Code: https://github.com/VAISR/OVGGT
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。