AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images

Xiangyu Sun, Haoyi Jiang, Liu Liu, Seungtae Nam, Gyeongjin Kang, Xinjie Wang, Wei Sui, Zhizhong Su, Wenyu Liu, Xinggang Wang, Eunbyung Park

CVPR 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 24 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 semantic loss (LSeg distillation) (ablation)Uni3R · ScanNetmIoU: 0.0183 -> 0.5484Improved
add semantic loss (LSeg distillation) (ablation)Uni3R · ScanNetPSNR: 25.38 -> 25.53No clear effect
add rendering loss (ablation)Uni3R · ScanNetconvergenceImproved
add point-map geometry loss (frozen VGGT) (ablation)Uni3R · ScanNetdepth rel error: 5.6 -> 3.9Improved
add point-map geometry loss (frozen VGGT) (ablation)Uni3R · ScanNetdepth tau: 48.2 -> 61.2Improved
add point-map geometry loss (frozen VGGT) (ablation)Uni3R · ScanNetPSNR/mIoU: 25.53 -> 25.53 PSNR; 0.5541 -> 0.5484 mIoUNo clear effect
add scale-invariant constraint (ablation)Uni3R · ScanNetPSNR: 24.95 -> 25.53Improved
add intrinsic embedding (ablation)Uni3R · ScanNetdepth tau: 42.5 -> 61.2Improved
fine-tune transformer layers instead of freezing all (ablation)Uni3R · ScanNetPSNR: 5.49 -> 25.53Improved
use Uni3R vs LSM for 2-view ScanNetUni3R · ScanNet 2 viewsdepth rel error / tau: 3.38 -> 3.87 rel; 67.77 -> 61.37 tauHurt
use Uni3R vs LSM for 2-view ScanNetUni3R · ScanNet 2 viewsPSNR and target mIoU: 24.39 -> 25.53; 0.5078 -> 0.5584Improved
use Uni3R vs NoPoSplat on RE10K 2 viewsUni3R · RE10K 2 viewsPSNR: 25.036 -> 25.074No clear effect

Later papers that compared with this method

4 later accepted papers report Uni3R as a baseline in their results tables; 4 of them report a better number on most of the results they share with it.

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