AI Paper Atlas

Research map / 3D vision / Gaussian splatting

S2D: Sparse to Dense Lifting for 3D Reconstruction with Minimal Inputs

Yuzhou Ji, Qijian Tian, He Zhu, Xiaoqi Jiang, Guangzhi Cao, Lizhuang Ma, Yuan Xie, Xin Tan

CVPR 2026 · 3D vision › Gaussian splatting · approach: Compact and efficient Gaussian splatting · 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 mixing module on input view instead of directly batching point cloud rendering (ablation)S2D artifact fixer · Artifact fixer guidance ablationPSNR: 19.0 -> 22.1Improved
add DINO guidance in the mixing module (ablation)S2D artifact fixer · Artifact fixer guidance ablationPSNR: 22.1 -> 23.0Improved
place mixing on image inputs rather than on VAE latents (ablation)S2D artifact fixer · Artifact fixer guidance ablationPSNR: 15.6 -> 23.0Improved
add reference view to point-cloud-only generation (dual guidance) (ablation)S2D artifact fixer · Artifact fixer guidance ablationPSNR: 12.7 -> 23.0Improved
add SSIM loss (ablation)S2D artifact fixer · Artifact fixer loss ablationPSNR: 20.1 -> 21.8Improved
add DINO loss (ablation)S2D artifact fixer · Artifact fixer loss ablationPSNR: 20.1 -> 20.5Improved
add CLIP loss (ablation)S2D artifact fixer · Artifact fixer loss ablationPSNR: 20.1 -> 20.1No clear effect
add DINO loss on top of SSIM loss (ablation)S2D artifact fixer · Artifact fixer loss ablationPSNR: 21.8 -> 22.0Improved
add S2D on top of 3DGS (ablation)3DGS · DL3DV (6 images)PSNR: 15.26 -> 23.2Improved
replace DIFIX fixer with S2D3DGS reconstruction · 3DOVS (1 image)PSNR: 14.10 -> 21.41Improved
replace DIFIX with S2D on lane shiftWaymo reconstruction · Waymo Open Dataset (lane shift 2m)FID: 60.2 -> 46.1Improved
add random sample drop (alpha 0.7) to reconstruction (ablation)S2D reconstruction · DL3DV scenesqualitativeImproved

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