AI Paper Atlas

Research map / 3D vision / Depth and stereo

Quanta Neural Networks: From Photons to Perception

Varun Sundar, Tianyi Zhang, Sacha Jungerman, Mohit Gupta

ICCV 2025 · 3D vision › Depth and stereo · approach: Spike and event camera reconstruction · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add intermediate learnable QNN layers beyond the sensor-proximal layer (ablation)QNN (adaptive integrator) · Depth estimation, dense computethreshold accuracy (%): 53.2 -> 71.2Improved
add intermediate learnable QNN layers beyond the sensor-proximal layer (ablation)QNN (adaptive integrator) · Point tracking, dense computeaverage Jaccard (%): 60.1 -> 75.9Improved
add intermediate learnable QNN layers beyond the sensor-proximal layer (ablation)QNN (adaptive integrator) · Intensity restoration i2k, dense computePSNR (dB): 30.3 -> 36.7Improved
use adaptive (Bayesian run-length) integration instead of fixed exponential smoothing (ablation)QNN with intermediate layers · Intensity restoration, eventful top-10%PSNR (dB): 32.7 -> 34.7Improved
use adaptive instead of fixed integration with intermediate layers, point tracking dense (ablation)QNN with intermediate layers · Point tracking, dense computeaverage Jaccard (%): 76.1 -> 75.9No clear effect
use adaptive instead of fixed integration without intermediate layers (ablation)QNN sensor-proximal only · Depth estimation, dense computethreshold accuracy (%): 50.8 -> 53.2Improved
run network incrementally with eventful computation (top-10%) instead of denseQNN with adaptive integrator · Depth estimationthreshold accuracy (%): 71.2 -> 65.5Mixed
replace reconstruction-then-depth pipeline with QNN denseDepthAnything-v2 QNN · Stress-ball depthlatency: 6000 ms -> 38 msImproved
add eventful computation on top of dense QNNDepthAnything-v2 QNN · Stress-ball depthGFLOP per output: 78 -> 26Improved
use change-driven sampling instead of uniform inference at comparable costQNN · Balloon burstoutput fidelity / runtime: 150x run-time speedupImproved
min-pool run-length estimates with 5x5 kerneladaptive integrator · qualitative (Figure 3)motion responsivenessImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy