← 研踪 PaperTrailarXiv:2611.21302 · v1
Déjà-Events: Multi-view 3D Geometry with Event Cameras via Sparsity-Aware Adaptive Gating
首次提交 2026-11-17 00:03
版本更新 2026-11-17 00:03
雷达观测 2026-11-17 16:10
摘要
Event cameras keep capturing structure where conventional cameras blur or saturate, which makes them attractive for 3D perception in fast or poorly lit scenes. Event datasets with dense 3D ground truth, however, are far smaller and less diverse than the image collections behind feed-forward 3D reconstruction models. We present Déjà-Events, an event-only model that predicts depth, camera pose and pointmaps from multiple views in a single forward pass. Rather than relying on scarce 3D labels, we distil it from Déjà View, a feed-forward RGB model that refines its tokens by repeatedly applying one shared transformer block. On paired RGB and event recordings, the event student learns to reproduce the frozen teacher's final tokens, which requires no depth or pose ground truth and trains only about 1% of its parameters. Because events are dense at edges and moving texture but nearly absent in textureless regions, we further introduce sparsity-aware adaptive gating, which adapts the shared block's gates to events and adjusts them per patch by event density, so that accuracy holds as refinement steps are added. Trained only on simulated data, Déjà-Events achieves the lowest pointmap error among the event-based methods we evaluate, on EventScape and zero-shot on the real MVSEC and DSEC datasets. On DSEC it halves the error of the strongest baseline (0.15 vs. 0.30 AbsRel) with about a tenth of its parameters. It also has the lowest depth error on EventScape and DSEC and the lowest trajectory error on EventScape.
作者备注:8 pages, 6 figures
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 · 2026-11-17 00:03 · 最新观测版本
Déjà-Events: Multi-view 3D Geometry with Event Cameras via Sparsity-Aware Adaptive Gating
Event cameras keep capturing structure where conventional cameras blur or saturate, which makes them attractive for 3D perception in fast or poorly lit scenes. Event datasets with dense 3D ground truth, however, are far smaller and less diverse than the image collections behind feed-forward 3D reconstruction models. We present Déjà-Events, an event-only model that predicts depth, camera pose and pointmaps from multiple views in a single forward pass. Rather than relying on scarce 3D labels, we distil it from Déjà View, a feed-forward RGB model that refines its tokens by repeatedly applying one shared transformer block. On paired RGB and event recordings, the event student learns to reproduce the frozen teacher's final tokens, which requires no depth or pose ground truth and trains only about 1% of its parameters. Because events are dense at edges and moving texture but nearly absent in textureless regions, we further introduce sparsity-aware adaptive gating, which adapts the shared block's gates to events and adjusts them per patch by event density, so that accuracy holds as refinement steps are added. Trained only on simulated data, Déjà-Events achieves the lowest pointmap error among the event-based methods we evaluate, on EventScape and zero-shot on the real MVSEC and DSEC datasets. On DSEC it halves the error of the strongest baseline (0.15 vs. 0.30 AbsRel) with about a tenth of its parameters. It also has the lowest depth error on EventScape and DSEC and the lowest trajectory error on EventScape.
查看此版本解读 →查看此版本原文 ↗