AI Paper Atlas

Research map / 3D vision / 3D generation

ClaraVid: A Holistic Scene Reconstruction Benchmark From Aerial Perspective With Delentropy-Based Complexity Profiling

Radu Beche, Sergiu Nedevschi

ICCV 2025 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 4 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 ClaraVid instead of Syndrone for trainingDPT segmentation · UAVidmIoU: 52.49 -> 57.50Improved
use ClaraVid instead of Syndrone for trainingDPT segmentation · UDDmIoU: 54.43 -> 58.22Improved
use ClaraVid instead of Syndrone for trainingDPT segmentation · SkyScapesmIoU: 42.75 -> 47.52Improved
use ClaraVid instead of Syndrone for trainingDPT segmentation · DronescapesmIoU: 34.11 -> 37.30Improved
use ClaraVid instead of Syndrone for trainingDPT segmentation · average synthetic-to-real gapgap (%): 22.34 -> 17.82Improved
replace Nerfacto with Gaussian Splattingreconstruction · ClaraVid NVS averagePSNR: 21.84 -> 23.67Improved
replace TensoRF with ZipNeRFreconstruction · ClaraVid NVS averageSSIM: 0.4144 -> 0.5966Improved
train on 90H, test on 45L instead of matched 45LGaussian Splatting · ClaraVid viewpointPSNR: 22.98 -> 17.88Hurt
train on 90H, test on 45L instead of matched 45L (ablation)Nerfacto · ClaraVid viewpointPSNR: 21.36 -> 18.23Hurt
train on 90H, test on 45L instead of matched 45LGaussian Splatting · ClaraVid viewpoint segmentationmIoU: 56.53 -> 36.68Hurt
use delentropy instead of Shannon or GLCM entropy as complexity measure (ablation)DSP · correlation with reconstruction errorPearson correlationImproved
higher mean delentropy of scenereconstruction methods · ClaraVid NVSPSNR: Rural #1 mu 4.18 PSNR 19.97 vs Urban #2 mu 3.29 PSNR 26.68 (Gaussian Splatting)Hurt

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