AI Paper Atlas

Research map / 3D vision / Depth and stereo

Spk2ImgNet: Learning To Reconstruct Dynamic Scene From Continuous Spike Stream

CVPR 2021 · 3D vision › Depth and stereo · approach: Spike and event camera reconstruction · 75 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
Use Spk2ImgNet's hierarchical reconstruction instead of TFISpike-camera reconstruction · Synthesized datasetPSNR: 24.94 -> 38.44Helped
Use Spk2ImgNet instead of TVSSpike-camera reconstruction · Synthesized datasetSSIM: 0.7452 -> 0.9767Helped
Use Spk2ImgNet instead of TVSSpike-camera reconstruction · Average real-life spike streamsNIQE: 7.4491 -> 3.8532Helped
Add spatially adaptive light inference (SALI) (ablation)Spk2ImgNet · Synthesized datasetPSNR: 37.03 -> 37.27Helped
Add pyramid deformable alignment (PDA) (ablation)Spk2ImgNet · Synthesized datasetPSNR: 37.03 -> 37.99Helped
Add reliability estimation (RE) to SALI and PDA (ablation)Spk2ImgNet · Synthesized datasetPSNR: 38.27 -> 38.44Helped
Add reliability estimation (RE) to SALI and PDA (ablation)Spk2ImgNet · Synthesized datasetSSIM: 0.9768 -> 0.9767Hurt

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