AI Paper Atlas

Research map / Video / Video segmentation and tracking

TransiT: Transient Transformer for Non-line-of-sight Videography

Ruiqian Li, Siyuan Shen, Suan Xia, Ziheng Wang, Xingyue Peng, Chengxuan Song, Yingsheng Zhu, Tao Wu, Shiying Li, Jingyi Yu

ICCV 2025 · Video › Video segmentation and tracking · approach: Spike and neuromorphic deblurring · 2 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
use TransiT instead of PnPreconstruction from 16x16 transients · Synthetic HumanPSNR: 19.92 -> 29.45Improved
use TransiT instead of f-kreconstruction from 16x16 transients · Synthetic PropellerSSIM: 0.1902 -> 0.8211Improved
use TransiT instead of PnPreconstruction · Synthetic CharacterED: 0.0923 -> 0.0520Improved
use TransiT instead of PnPreconstruction · Synthetic PropellerPSNR: 11.39 -> 20.91Improved
fine-tune pretrained TransiT on distortion-free data and compare to USM (ablation)TransiT · Static HumanPSNR: 24.24 -> 26.39Improved
fine-tune pretrained TransiT on distortion-free data and compare to USM (ablation)TransiT · Static PropellerPSNR: 21.92 -> 18.61Hurt
fine-tune pretrained TransiT on distortion-free data and compare to USM (ablation)TransiT · Static CharacterPSNR: 25.19 -> 25.49No clear effect
compress temporal axis of transients to 32-dim featureTransiT · NLOS reconstructionqualityNo clear effect

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