Lune

CVPR Findings2026

FALCON: Fast Adaptive Lightweight Computation of Intensities and Events for Depth Estimation

Sankarshana Venugopal, Mohammad Mostafavi, Jonghyun Choi

Abstract

Event-based stereo depth estimation promises high-speed, robust perception under challenging conditions, but fusing events with intensity frames incurs heavy computational costs, hindering real-time deployment. We introduce FAL-CON: a Fast Adaptive Lightweight Computation framework that co-designs spiking neuron dynamics (via LIF neurons) with 1×1 convolutional event representations and a streamlined stereo backbone for efficient depth estimation. Our per-pixel spiking encoders capture temporal dynamics with over 1000× fewer FLOPs than prior modules, while our σ-matching heuristic optimizes event grouping to minimize blur. FALCON achieves state-of-the-art accuracy on DSEC (MAE 0.356) and MVSEC (MDE 11.7 cm) at 32.2 FPS and 72.8 FPS, respectively, establishing a new real-time benchmark for neuromorphic vision applications. Our code is publicly available at https://github.com/snumprlab/falcon.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Stereo Depth from Events Cameras: Concentrate and Focus on the Future cites Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds
  • Discrete time convolution for fast event-based stereo cites Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds
  • Discrete time convolution for fast event-based stereo cites Deep Event Stereo Leveraged by Event-to-Image Translation
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on8

  1. Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation LearningWeixin Liang, Yuhui Zhang, Yongchan Kwon, Serena Yeung et al.NeurIPS 2022 · 834 citations
  2. Stereo Depth from Events Cameras: Concentrate and Focus on the FutureYeongwoo Nam, S. Mohammad Mostafavi I., Kuk-Jin Yoon, Jonghyun ChoiCVPR 2022 · 56 citations
  3. Event-Intensity Stereo: Estimating Depth by the Best of Both WorldsS. Mohammad Mostafavi I., Kuk-Jin Yoon, Jonghyun ChoiICCV 2021 · 45 citations
  4. Deep Event Stereo Leveraged by Event-to-Image TranslationSoikat Hasan Ahmed, Hae Woong Jang, S. M. Nadim Uddin, Yong Ju JungAAAI 2021 · 41 citations
  5. Discrete time convolution for fast event-based stereoKaixuan Zhang, Kaiwei Che, Jianguo Zhang, Jie Cheng et al.CVPR 2022 · 34 citations

Related papers

  1. SpikeStereoNet: A Brain-Inspired Framework for Stereo Depth Estimation from Spike StreamsZhuoheng Gao, Yihao Li, Jiyao Zhang, Rui Zhao et al.ICLR 2026 · 2 citations
  2. DERD-Net: Learning Depth from Event-based Ray DensitiesDiego de Oliveira Hitzges, Suman Ghosh, Guillermo GallegoNeurIPS 2025 · 6 citations
  3. Active Event-based Stereo VisionJianing Li, Yunjian Zhang, Haiqian Han, Xiangyang JiCVPR 2025
  4. CREST: An Efficient Conjointly-trained Spike-driven Framework for Event-based Object Detection Exploiting Spatiotemporal DynamicsRuixin Mao, Aoyu Shen, Lin Tang, Jun ZhouAAAI 2025
  5. 240FPS Stereo Vision from Monocular Mixed SpikesYeliduosi Xiaokaiti, Yakun Chang, Yang Bai, Zhaojun Huang et al.CVPR 2026
Dusk over the sea between two cliffs drawn in fine vertical lines