ChatPaper.aiChatPaper

ZPressor:面向可扩展前馈3DGS的瓶颈感知压缩技术

ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS

May 29, 2025
作者: Weijie Wang, Donny Y. Chen, Zeyu Zhang, Duochao Shi, Akide Liu, Bohan Zhuang
cs.AI

摘要

前馈式三维高斯泼溅(3DGS)模型近期作为新颖视角合成的一种有前景解决方案崭露头角,其能够实现无需逐场景3DGS优化的一步推理。然而,这些模型的可扩展性从根本上受限于其编码器的有限容量,随着输入视角数量的增加,导致性能下降或内存消耗过度。在本研究中,我们通过信息瓶颈原则的视角分析了前馈式3DGS框架,并引入了ZPressor——一个轻量级、与架构无关的模块,它能够高效地将多视角输入压缩至一个紧凑的潜在状态Z,该状态在保留场景关键信息的同时摒弃冗余。具体而言,ZPressor通过将视角划分为锚点集和支持集,并利用交叉注意力机制将支持视角的信息压缩至锚点视角,形成压缩后的潜在状态Z,使得现有前馈式3DGS模型能够在80GB GPU上扩展至超过100个480P分辨率的输入视角。我们展示了将ZPressor集成到多个先进的前馈式3DGS模型中,在DL3DV-10K和RealEstate10K两大基准测试上,不仅在中度输入视角下持续提升性能,还在密集视角设置下增强了鲁棒性。视频成果、代码及训练模型均可在我们的项目页面获取:https://lhmd.top/zpressor。
English
Feed-forward 3D Gaussian Splatting (3DGS) models have recently emerged as a promising solution for novel view synthesis, enabling one-pass inference without the need for per-scene 3DGS optimization. However, their scalability is fundamentally constrained by the limited capacity of their encoders, leading to degraded performance or excessive memory consumption as the number of input views increases. In this work, we analyze feed-forward 3DGS frameworks through the lens of the Information Bottleneck principle and introduce ZPressor, a lightweight architecture-agnostic module that enables efficient compression of multi-view inputs into a compact latent state Z that retains essential scene information while discarding redundancy. Concretely, ZPressor enables existing feed-forward 3DGS models to scale to over 100 input views at 480P resolution on an 80GB GPU, by partitioning the views into anchor and support sets and using cross attention to compress the information from the support views into anchor views, forming the compressed latent state Z. We show that integrating ZPressor into several state-of-the-art feed-forward 3DGS models consistently improves performance under moderate input views and enhances robustness under dense view settings on two large-scale benchmarks DL3DV-10K and RealEstate10K. The video results, code and trained models are available on our project page: https://lhmd.top/zpressor.
PDF45May 30, 2025