StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression

• URL: http://arxiv.org/abs/2604.15237v2
• Date: Fri, 17 Apr 2026 17:56:45 GMT
• Title: StreamCacheVGGT: Streaming Visual Geometry Transformers with Robust Scoring and Hybrid Cache Compression
• Abstract summary: StreamCacheVGGT is a training-free framework that reimagines cache management.<n>It delivers superior reconstruction accuracy and long-term stability while strictly adhering to constant-cost constraints.
• Score: 39.0869112189715
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reconstructing dense 3D geometry from continuous video streams requires stable inference under a constant memory budget. Existing $O(1)$ frameworks primarily rely on a ``pure eviction'' paradigm, which suffers from significant information destruction due to binary token deletion and evaluation noise from localized, single-layer scoring. To address these bottlenecks, we propose StreamCacheVGGT, a training-free framework that reimagines cache management through two synergistic modules: Cross-Layer Consistency-Enhanced Scoring (CLCES) and Hybrid Cache Compression (HCC). CLCES mitigates activation noise by tracking token importance trajectories across the Transformer hierarchy, employing order-statistical analysis to identify sustained geometric salience. Leveraging these robust scores, HCC transcends simple eviction by introducing a three-tier triage strategy that merges moderately important tokens into retained anchors via nearest-neighbor assignment on the key-vector manifold. This approach preserves essential geometric context that would otherwise be lost. Extensive evaluations on five benchmarks (7-Scenes, NRGBD, ETH3D, Bonn, and KITTI) demonstrate that StreamCacheVGGT sets a new state-of-the-art, delivering superior reconstruction accuracy and long-term stability while strictly adhering to constant-cost constraints.

Related papers

• DepthWeave-KV: Token-Adaptive Cross-Layer Residual Factorization for Long-Context KV Cache Compression [0.0]
  DepthWeave-KV is a token-adaptive cache compression method that factorizes key and value states across neighboring transformer layers.<n> DepthWeave-KV achieves near-full-output task quality with substantially lower memory use.
  arXiv  Detail & Related papers  (2026-07-07T17:29:01Z)
• GHOST: Geometry-Hierarchical Online Streaming Token Eviction for Efficient 3D Reconstruction [23.110378663548335]
  Streaming 3D reconstruction from long monocular video sequences requires maintaining a keyvalue (KV) cache.<n>GHOST is a training-free KV cache management framework that exploits the model's own 3D geometry outputs to evict redundant tokens online.<n> Experiments on various benchmarks show that GHOST preserves excellent reconstruction quality while cutting the KV cache by nearly half and delivering 1.75x faster inference.
  arXiv  Detail & Related papers  (2026-05-15T11:07:33Z)
• StructKV: Preserving the Structural Skeleton for Scalable Long-Context Inference [38.75965915663233]
  We propose StructKV, a structure-aware KV cache compression framework.<n>First, Global In-Degree Centrality aggregates attention patterns across the network depth to identify global information hubs.<n>Second, Dynamic Pivot Detection utilizes information-theoretic metrics to adaptively locate the optimal layer for compression.
  arXiv  Detail & Related papers  (2026-04-08T07:10:35Z)
• LG-HCC: Local Geometry-Aware Hierarchical Context Compression for 3D Gaussian Splatting [77.81227097905865]
  Anchor-based 3DGS compression schemes reduce gaussian redundancy through some advanced context models.<n>We propose a Local Geometry-aware Hierarchical Context Compression framework for 3DGS that incorporates inter-anchor geometric correlations into anchor pruning and entropy coding for compact representation.<n>Experiments show that LG-HCC effectively alleviates structural preservation issues,achieving superior geometric integrity and rendering fidelity while reducing storage by up to 30.85x compared to the Scaffold-GS baseline on the Mip-NeRF360 dataset.
  arXiv  Detail & Related papers  (2026-03-30T13:39:35Z)
• STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction [16.772404929988507]
  3D reconstruction from streaming inputs requires both long-term temporal consistency and efficient memory usage.<n> STAC is a framework for streaming 3D reconstruction with large causal transformers.<n> experiments show that STAC achieves state-of-the-art reconstruction quality while reducing memory consumption by nearly 10x and accelerating inference by VG 4x.
  arXiv  Detail & Related papers  (2026-03-18T06:36:46Z)
• LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory [97.14005794889134]
  We present LoGeR, a novel architecture that scales dense 3D reconstruction to extremely long sequences without post-optimization.<n>LoGeR processes video streams in chunks, leveraging strong bidirectional priors for high-fidelity intra-chunk reasoning.<n>This memory architecture enables LoGeR to be trained on sequences of 128 frames, and generalize up to thousands of frames during inference.
  arXiv  Detail & Related papers  (2026-03-03T18:55:37Z)
• HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference [14.17979669446161]
  We propose HeteroCache, a training-free dynamic compression framework.<n>We show that HeteroCache achieves state-of-the-art performance on multiple long-context benchmarks and accelerates decoding by up to $3times$ compared to the original model in the 224K context.
  arXiv  Detail & Related papers  (2026-01-20T07:35:06Z)
• CSGaussian: Progressive Rate-Distortion Compression and Segmentation for 3D Gaussian Splatting [57.73006852239138]
  We present the first unified framework for rate-distortion-optimized compression and segmentation of 3D Gaussian Splatting (3DGS)<n>Inspired by recent advances in rate-distortion-optimized 3DGS compression, this work integrates semantic learning into the compression pipeline to support decoder-side applications.<n>Our scheme features a lightweight implicit neural representation-based hyperprior, enabling efficient entropy coding of both color and semantic attributes.
  arXiv  Detail & Related papers  (2026-01-19T08:21:45Z)
• PackCache: A Training-Free Acceleration Method for Unified Autoregressive Video Generation via Compact KV-Cache [61.57938553036056]
  We introduce PackCache, a training-free KV-cache management method that compacts the KV cache through three coordinated mechanisms.<n>In terms of efficiency, PackCache accelerates end-to-end generation by 1.7-2.2x on 48-frame long sequences.
  arXiv  Detail & Related papers  (2026-01-07T19:51:06Z)
• CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing [54.34080239841088]
  CommonKV is a training-free method for cross-layer KV cache compression through adjacent parameters sharing.<n>We show that the proposed method consistently outperforms existing low-rank and cross-layer approaches at various compression ratios.
  arXiv  Detail & Related papers  (2025-08-22T06:55:45Z)
• Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing [41.792908098945766]
  We present Krul, a multi-turn LLM inference system that enables accurate and efficient KV cache restoration.<n>Krul selects compression strategies based on attention similarity across layer pairs and uses a recomputation-loading pipeline to restore the KV cache.<n>It achieves a 1.5x-2.68x reduction in time-to-first-token (TTFT) and a 1.33x-2.35x reduction in KV cache storage.
  arXiv  Detail & Related papers  (2025-07-10T01:51:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.