AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Language-Driven Physics-Based Scene Synthesis and Editing via Feature Splatting

Ri-Zhao Qiu, Ge Yang, Weijia Zeng, Xiaolong Wang

ECCV 2024 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views · 30 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 SAM-based mask pooling and DINOv2 regularization to CLIP feature distillation (ablation)Feature Splatting · LERF localization (2D)localization accuracy: 73.0% -> 81.7%Improved
add DINOv2 regularization (without SAM) on top of CLIP-only (ablation)Feature Splatting · LERF localization (2D)localization accuracy: 73.0% -> 71.4%Hurt
add DINO regularization (ablation)Feature Splatting · Collected datasets, validation viewsCLIP feature loss (val): 0.048 -> 0.046Improved
add DINO regularization (ablation)Feature Splatting · Collected datasets, training viewsCLIP feature loss (train): 0.029 -> 0.032Hurt
add feature splatting to Gaussian splattingVanilla GS · Collected datasetsPSNR: 26.45 -> 26.47No clear effect
add feature splatting to Gaussian splattingVanilla GS · Collected datasetsFPS: 129 -> 102Hurt
add custom CUDA kernel optimizations (half2, shared gradient buffer, interleaved memory) (ablation)Feature rasterizer, dim 768 · DB dataset, 1000 iterationstraining time: 3.21 -> 1.21Improved
use low-dimensional (32) latent features with a shallow MLP decoder instead of 256 dimsFeature Splatting · DB dataset, 1000 iterationstraining time: 0.41 -> 0.06Improved
add implicit volume preservation (densified surface and transparent internal particles) (ablation)GS-Taichi-MPM · bouncing ball scenequalitative physical plausibilityImproved
estimate Gaussian rotation from nearest-neighbor displacement instead of deformation gradient (ablation)GS-Taichi-MPM · sculpture under large deformationqualitative surface artifactsImproved
use feature splatting instead of LERF for 2D localizationLERF baseline · LERF localization (2D)localization accuracy: 80.3% -> 81.7%Improved

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