AI Paper Atlas

Research map / 3D vision / Gaussian splatting

IDESplat: Iterative Depth Probability Estimation for Generalizable 3D Gaussian Splatting

Wei Long, Haifeng Wu, Shiyin Jiang, Jinhua Zhang, Xinchun Ji, Shuhang Gu

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 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
add Gaussian Focused Module (ablation)IDESplat baseline · RealEstate10K (20k-iter)PSNR: 26.31 -> 26.63Improved
add 3 iterations of depth probability boosting units (ablation)IDESplat baseline · RealEstate10K (20k-iter)PSNR: 26.31 -> 26.88Improved
add depth probability boosting strategy to the iterative process (ablation)IDESplat (IDE(3)) · RealEstate10K (20k-iter)PSNR: 26.88 -> 27.34Improved
add GFM to IDE(3)+DPBS (ablation)IDESplat · RealEstate10K (20k-iter)PSNR: 27.34 -> 27.56Improved
go from single warp to 1 iteration (ablation)IDESplat · RealEstate10K (20k-iter)PSNR: 26.63 -> 27.08Improved
increase iterations from 3 to 4 (ablation)IDESplat · RealEstate10K (20k-iter)PSNR: 27.56 -> 27.64Improved
increase iterations from 3 to 4 (ablation)IDESplat · RealEstate10K (20k-iter)Time (s): 0.110 -> 0.132Hurt
IDESplat versus DepthSplat in model sizeIDESplat · RealEstate10KParams (M): 354 -> 37.6Improved
IDESplat versus DepthSplat in inference timeIDESplat · RealEstate10KTime (s): 0.082 -> 0.110Hurt
IDESplat versus DepthSplat zero-shot transferIDESplat · RE10K->DTUPSNR: 15.38 -> 18.33Improved
IDESplat versus DepthSplat depth estimationIDESplat · ScanNet depthAbs Rel: 0.045 -> 0.039Improved
IDESplat versus MonoSplat on ACID (in-domain)IDESplat · ACIDSSIM: 0.864 -> 0.866No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 4 of 4 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