AI Paper Atlas

Research map / Point clouds / Shape and surface completion

RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians

Shenxing Wei, Jinxi Li, Yafei Yang, Siyuan Zhou, Bo Yang

ICCV 2025 · Point clouds › Shape and surface completion · approach: Distance-function surface reconstruction · 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
use multiple raylets (T=5) instead of one in training (ablation)RayletDF · ScanNet/ScanNet++ (3D Gaussians)ADE (m): 0.174 -> 0.145Improved
add confidence score s_l to blender (ablation)RayletDF · ScanNet/ScanNet++ (3D Gaussians)ADE (m): 0.170 -> 0.145Improved
use softmax-normalized confidence instead of sigmoid (ablation)RayletDF · ScanNet/ScanNet++ (3D Gaussians)ADE (m): 0.164 -> 0.145Improved
use softmax-normalized confidence instead of alpha blending (ablation)RayletDF · ScanNet/ScanNet++ (3D Gaussians)ADE (m): 0.156 -> 0.145Improved
include both xyz and relative position of neighbors (ablation)RayletDF · ScanNet/ScanNet++ (3D Gaussians)ADE (m): 0.148 -> 0.145Improved
use K=5 neighbors instead of K=1 (ablation)RayletDF · ScanNet/ScanNet++ (3D Gaussians)ADE (m): 0.151 -> 0.145Improved
increase neighbors from K=5 to K=20 (ablation)RayletDF · ScanNet/ScanNet++ (3D Gaussians)ADE (m): 0.145 -> 0.152Hurt
increase test-time raylets from T=1 to T=10RayletDF · ScanNet/ScanNet++ (3D Gaussians)ADE (m): 0.177 -> 0.140Improved
increase test-time raylets from T=5 to T=20RayletDF · MultiScan (unseen)ADE (m): 0.259 -> 0.247Improved
increase test-time raylets from T=10 to T=20RayletDF · ScanNet/ScanNet++ (3D Gaussians)ADE (m): 0.140 -> 0.141No clear effect
replace RayDF with RayletDF, cross-dataset (train ScanNet, test MultiScan)point cloud input · MultiScanADE (m): 0.349 -> 0.130Improved
replace RayDF with RayletDF in domain3D Gaussians input · ARKitScenesADE (m): 0.183 -> 0.115Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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