AI Paper Atlas

Research map / 3D vision / Gaussian splatting

LangField4D: Learning Identity-Adaptive and Spatio-Temporal Continuous 4D Language Fields for Dynamic Scenes

Yichao Xu, Qiaowei Miao, Jinsheng Quan, Wei Yang, Zhihui Li, Yawei Luo

CVPR 2026 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction

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
replace MLP decoders with TetraPlane representation (ablation)LangField4D (without IdaGG) · HyperNeRF time-varyingvIoU: 51.61 -> 60.03Improved
replace MLP decoders with TetraPlane representation (ablation)LangField4D (without IdaGG) · HyperNeRF time-varyingAcc: 71.95 -> 80.97Improved
replace MLP decoders with TetraPlane representation (ablation)LangField4D (without IdaGG) · HyperNeRF time-agnosticmIoU: 80.85 -> 81.94Improved
add Identity-Adaptive Gaussian Grouping (ablation)TetraPlane · HyperNeRF time-agnosticmIoU: 81.94 -> 83.09Improved
add Identity-Adaptive Gaussian Grouping (ablation)MLP decoders · HyperNeRF time-agnosticmIoU: 80.85 -> 82.63Improved
add Identity-Adaptive Gaussian Grouping (ablation)TetraPlane · HyperNeRF time-varyingvIoU: 60.03 -> 64.31Improved
add Identity-Adaptive Gaussian Grouping (ablation)MLP decoders · HyperNeRF time-varyingAcc: 71.95 -> 70.79Hurt
add Identity-Adaptive Gaussian Grouping (ablation)MLP decoders · HyperNeRF time-varyingvIoU: 51.61 -> 52.59Improved
add IdaGG on Gaussian identity (ablation)TetraPlane · HyperNeRF time-agnosticmAcc: 98.29 -> 98.37No clear effect
full LangField4D vs 4DLangSplat4DLangSplat · Neu3D time-agnosticmIoU: 55.18 -> 71.62Improved
full LangField4D vs 4DLangSplat4DLangSplat · HyperNeRF time-sensitive (overall)vIoU: 47.04 -> 64.31Improved

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