AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MAC-Splat: Multi-Attribute Consistency for High-Fidelity Sparse-View Reconstruction

Jinqian Yang, Yichen Wu, Wanhua Li, Haokun Lin, Renzhen Wang, Xiangchu Feng, Xixi Jia

ECCV 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 2 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 MAC loss (ablation)MAC-Splat · ScanNet++ Very WidePSNR: 17.12 -> 21.34Improved
add MAC loss without DINOv3 fusion (ablation)MAC-Splat backbone · ScanNet++ Very WidePSNR: 17.12 -> 20.23Improved
add Residual Semantic Fusion with DINOv3 (ablation)MAC-Splat · ScanNet++ Very WidePSNR: 20.23 -> 21.34Improved
add Residual Semantic Fusion with DINOv3 (ablation)MAC-Splat · ScanNet++ ClosePSNR: 20.57 -> 22.76Improved
add Residual Semantic Fusion with DINOv3 (ablation)MAC-Splat · ScanNet++ CloseLPIPS: 0.237 -> 0.146Improved
add MAC loss (ablation)MAC-Splat · ScanNet++ ClosePSNR: 19.94 -> 22.76Improved
add MAC loss (ablation)MAC-Splat · ScanNet++ WideLPIPS: 0.186 -> 0.142Improved
add DINOv3 descriptor fusion (ablation)MAC-Splat · ScanNet++ (ablation)LPIPS: ~22%Improved
MAC-Splat vs Splatt3R (adds MAC loss and fused correspondences)Splatt3R · ScanNet++ (average of four splits)PSNR: more than 4.5 dBImproved
MAC-Splat vs Splatt3RSplatt3R · ScanNet++ (average of four splits)LPIPS: about 44%Improved
wider baseline (Close to Very Wide) for MAC-SplatMAC-Splat · ScanNet++PSNR: 22.76 -> 21.34No clear effect
wider baseline (Close to Very Wide) for PixelSplatPixelSplat · ScanNet++PSNR: 23.98 -> 15.36Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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