← 研踪 PaperTrailarXiv:2611.20241 · v1
EvoMem3D: Adaptive-Depth Temporal Representation Memory for Multi-Camera 3D Detection
首次提交 2026-11-16 04:45
版本更新 2026-11-16 04:45
雷达观测 2026-11-17 17:12
摘要
Modern multi-camera 3D detectors increasingly rely on large Vision Transformer (ViT) image encoders, making repeated full-depth encoding a dominant inference cost even though adjacent driving frames are highly redundant. We present EvoMem3D, an adaptive-depth temporal framework that caches the most recent full-depth detector-interface appearance representation as a read-only anchor and combines it with policy-selected partial features from the current frame. A lightweight pre-encoding controller chooses among semantic encoder exits before image processing, allocating shallow computation to stable frames and deeper computation when the visual state changes. To reuse appearance without carrying stale geometry, we decouple temporal appearance from geometric alignment: current-frame calibration defines the decoder geometry at every timestamp, while a motion-conditioned positional adapter accounts for anchor-to-current ego motion. On nuScenes, EvoMem3D achieves 61.50 NDS and 52.76 mAP while reducing end-to-end latency from 364.4 to 168.7 ms (x2.16) relative to standard dense DETR3D. With StreamPETR, it reaches 61.36 NDS and 52.55 mAP at a x1.92 speedup. Controlled studies isolate the effects of current evidence, temporal reuse, memory correction, and adaptive routing, while our audit confirms that the policy learns to distinguish semantic driving regimes.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-16 04:45 · 最新观测版本
EvoMem3D: Adaptive-Depth Temporal Representation Memory for Multi-Camera 3D Detection
Modern multi-camera 3D detectors increasingly rely on large Vision Transformer (ViT) image encoders, making repeated full-depth encoding a dominant inference cost even though adjacent driving frames are highly redundant. We present EvoMem3D, an adaptive-depth temporal framework that caches the most recent full-depth detector-interface appearance representation as a read-only anchor and combines it with policy-selected partial features from the current frame. A lightweight pre-encoding controller chooses among semantic encoder exits before image processing, allocating shallow computation to stable frames and deeper computation when the visual state changes. To reuse appearance without carrying stale geometry, we decouple temporal appearance from geometric alignment: current-frame calibration defines the decoder geometry at every timestamp, while a motion-conditioned positional adapter accounts for anchor-to-current ego motion. On nuScenes, EvoMem3D achieves 61.50 NDS and 52.76 mAP while reducing end-to-end latency from 364.4 to 168.7 ms (x2.16) relative to standard dense DETR3D. With StreamPETR, it reaches 61.36 NDS and 52.55 mAP at a x1.92 speedup. Controlled studies isolate the effects of current evidence, temporal reuse, memory correction, and adaptive routing, while our audit confirms that the policy learns to distinguish semantic driving regimes.
查看此版本解读 →查看此版本原文 ↗