Skip to content
Preprint

LiFR v2: Completion-Augmented Event Propagation for High-Rate Dense Prediction

Sep 2026 · 0 citations · 58 references
Computer Science

TL;DR

LiFR v2 is presented, a unified propagation-completion-memory framework for causal anytime and streaming dense prediction from an RGB keyframe and events and introduces an Event-Guided Completion Module (EGCM) and a History Retrieval Module (HRM) to reuse completed representations across successive queries.

Abstract

High-rate dense perception in dynamic environments is limited by the low update rate of RGB cameras, as rapid scene changes can occur between frames. Event cameras offer temporally dense but spatially sparse measurements, complementary to spatially dense RGB observations. Direct fusion cannot fully exploit this complementarity, while event-guided propagation fails on newly appearing or disoccluded regions without valid RGB support. We present LiFR v2, a unified propagation-completion-memory framework for causal anytime and streaming dense prediction from an RGB keyframe and events. LiFR v2 introduces an Event-Guided Completion Module (EGCM) to recover task-relevant representations where propagation is unsupported, and a History Retrieval Module (HRM) to reuse completed representations across successive queries. The framework supports semantic segmentation, monocular depth estimation, and multi-task dense prediction, and we further introduce SHF-Emerge to evaluate rapid object emergence and disocclusion. LiFR v2 achieves 74.37% mIoU on DSEC and 56.13% on SHF-Emerge, improving LiFR-Seg by 1.85 percentage points on the latter, while reducing SHF-Emerge depth RMSE from 1.564 m to 1.118 m over the propagation baseline. It also exceeds 100 FPS for both segmentation and depth, demonstrating accurate and efficient high-rate perception beyond RGB frame rates.

View source

Similar papers

Nov 2026

MonoTemp3D: Lightweight Short-Horizon Temporal Enhancement for Streaming Monocular 3D Car Detection

Monocular 3D object detection (M3OD) is attractive for autonomous driving and resource-constrained robotic platforms due to its low hardware cost. While temporal cues can alleviate depth ambiguity, dense feature matching and explicit motion estimation introduce substantial latency and limit low-latency deployment. To a...

Jia-Ying Li, Tong Liu, Xiao-Dong Guo et al. · 0 citations
Preprint Sep 2026

DAPEVO: Deep Adaptive Patch Frame-Event Visual Odometry

DAPEVO is a learned visual odometry system that estimates image and event correspondences independently at shared patch locations and fuses their correlation evidence before motion refinement, and a learned scalar gate combines modality-specific correlation embeddings for each patch--frame edge before a shared recurren...

Luca Gandolfi, Simone Nascivera, R. Pellerito et al. · 0 citations
Preprint Oct 2026

UniDynamics: Event-RGB Fusion for Unified Future 4D Dynamic Scene Generation

We propose UniDynamics, a diffusion-based framework for future 4D dynamic scenes (RGB, depth, and optical flow) generation from a single event-RGB pair, without requiring long histories or control priors as in existing methods, while explicitly modeling future motion fields. The core idea is to leverage event streams t...

Dai-Kun Liu, Xin Zhan, Teng Wang et al. · 0 citations
Preprint Oct 2026

Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth Estimation

Event cameras hold excellent dynamic properties, showing great potential for monocular depth estimation (MDE). However, existing methods mainly improve performance by optimizing contextual features, but still struggle with the ill-posed and nonlinear nature of direct full-depth regression. In this paper, we propose Hyp...

Dai-Kun Liu, Teng Wang, Chang-Yin Sun · 1 citation
Preprint Sep 2026

Efficient Multi-Timescale Event Representations for Feed-Forward Object Detection

This work investigates how temporal information can be encoded directly within the event representation, proposing a confidence-normalized continuous multi-timescale representation based on logarithmic B-spline temporal encoding together with a geometry-aware local confidence mechanism that exploits the spatial structu...

Fredrik Lundell, Per-Erik Forssén, Mårten Wadenbäck et al. · 1 citation
#artificial intelligence Preprint Sep 2026

DiffWAM: A Fast and Efficient Navigation World Action Model

DiffWAM is presented, a geometry-conditioned navigation world-action model that directly transforms multi-level predictive features into continuous camera trajectories, providing a direct alternative to generate-then-reconstruct navigation pipelines.

Morui Zhu, Yu-Ze Wu, Xi-Jie Huang et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.