Evict3R: Training-Free Token Eviction for Memory-Bounded Streaming Visual Geometry Transformers
Streaming visual transformers like StreamVGGT achieve strong 3D perception but suffer from unbounded growth of key value (KV) memory, which limits scalability. We propose a training-free, inference-time token eviction policy that bounds memory by discarding redundant tokens while keeping the most informative ones. Our method uses significantly less memory with little to no drop in accuracy: on 7-Scenes with long sequences it reduces peak memory from 18.63 GB to 9.39 GB while accuracy and completeness drop by only 0.003. Under strict memory budgets, eviction enables denser frame sampling, which improves reconstruction accuracy compared to the baseline. Experiments across video depth estimation (Sintel, KITTI), 3D reconstruction (7-Scenes, NRGBD), and camera pose estimation (Sintel, TUM-dynamics) show that our approach closely matches StreamVGGT at a fraction of the memory and makes long-horizon streaming inference more practical.
Code (0)
등록된 구현이 없습니다.
Tasks
Camera Pose Estimation3D ReconstructionDepth EstimationSimilar Papers 제목 키워드 기반
LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning
Large Language Models (LLMs) exhibit enhanced reasoning capabilities by employing Chain-of-Thought (CoT). However, the extended reasoning sequences introduce significant GPU memory overhead due to increased key-value (KV…
GPUCAOTE: KV Caching through Attention Output Error based Token Eviction
While long context support of large language models has extended their abilities, it also incurs challenges in memory and compute which becomes crucial bottlenecks in resource-restricted devices. Token eviction, a widely…
Forget Without Compromise: Nexus Sampling for Streaming KV-Cache Eviction Under Fixed Budgets
Long-context and agentic LLM workloads push the KV cache past any fixed memory budget, forcing the inference stack to permanently evict tokens at every step of a continuous-inference stream. Existing methods all share th…
Learning What Not to Forget: Long-Horizon Agent Memory from a Few Kilobytes of Learning
Long-running language-model systems accumulate interaction history that outgrows the context window, so they must continually evict. When an eviction policy drops a load-bearing detail, for example an access token issued…
PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
KV caching significantly improves the efficiency of Large Language Model (LLM) inference by storing attention states from previously processed tokens, enabling faster generation of subsequent tokens. However, as sequence…