AI Paper Atlas

Research map / 3D vision / Depth and stereo

SP-TransientBench: A Real-Captured Single Photon Perception Benchmark

Hongzhou Dong, Zili Zhang, Ziting Wen, Yiheng Qiang, Runrong Deng, Wenle Dong, Ziwen Jiang, Xinyang Li, Rui Lu, Shuoyao Sun, Wenyu Wang, Ziyi Xia and 3 more

ECCV 2026 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 0 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 histogram preprocessing before point-cloud segmentation (ablation)PointNet++ · STB 3D semantic segmentationmIoU: 49.16 -> 51.31Improved
add histogram preprocessing (thresholding) before segmentation (ablation)PointMLP · STB 3D semantic segmentationmIoU: 49.11 -> 52.22Improved
add SSPINET preprocessing before segmentation (ablation)PointNeXt · STB 3D semantic segmentationmIoU: 41.05 -> 41.54No clear effect
add Matched Filtering preprocessing (ablation)PointNeXt · STB 3D semantic segmentationOA: 88.45 -> 87.07Hurt
swap PointNet++ backbone for PointNeXt with no preprocessing (ablation)segmentation pipeline · STB 3D semantic segmentationmIoU: 49.16 -> 41.05Hurt
pretrain on simulated ScanNet transients then finetune, 10% real data (ablation)PointNet++ · STB segmentation, 10% real datamIoU: 33.19 -> 36.57Improved
pretrain on simulated ScanNet transients then finetune, 20% real data (ablation)PointNet++ · STB segmentation, 20% real datamIoU: 37.98 -> 41.39Improved
pretrain on simulated ScanNet transients then finetune, 100% real data (ablation)PointNet++ · STB segmentation, 100% real datamIoU: 52.24 -> 51.20No clear effect
use learning-based SSPINET instead of model-based Shin for depthdepth estimation · STB depth estimationRecall 1 bin (%): 25.97 -> 44.27Improved
loosen recall tolerance from 1 bin to 5 binsSSPINET · STB depth estimationRecall (%): 44.27 -> 93.68Improved
TransientNeRF versus Transientangelomulti-view reconstruction · STB multi-view reconstruction (10 views)Histogram PSNR: 45.4251 vs 41.5735Mixed

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