AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Flash-Refine: Frustum-Guided Local Incremental Learning for Efficient 3D Gaussian Splatting Completion

Nuocheng Ji, Hanyang Zhuang, Chunxiang Wang, Ming Yang

ECCV 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 point-wise consensus masking with gradient lock (ablation)Flash-Refine · Counter (Kept images)PSNR (dB): 20.33 -> 27.47Improved
add adaptive depth-bounded prior to frustum masking (ablation)Flash-Refine · Counter (Kept images)PSNR (dB): 24.04 -> 27.47Improved
add anti-deletion shield (ablation)Flash-Refine · Counter (Kept images)PSNR (dB): 20.87 -> 27.47Improved
add anti-deletion shield (ablation)Flash-Refine · Counter (Dropped images)PSNR (dB): 26.22 -> 29.66Improved
add mask (gradient lock) vs naive fine-tuningFlash-Refine · Bedroom (Kept images)PSNR (dB): 24.30 -> 28.71Improved
Flash-Refine vs naive fine-tuning on dropped viewsFlash-Refine · Bedroom (Dropped images)PSNR (dB): 26.08 -> 27.17Improved
Flash-Refine vs geometric stitchingFlash-Refine · DrJohnson (Kept images)PSNR (dB): 25.82 -> 27.57Improved
Flash-Refine vs full retrain on Counter dropped viewsFlash-Refine · Counter (Dropped images)PSNR (dB): 31.03 -> 29.66Hurt
Flash-Refine repair vs base model on kept viewsFlash-Refine · Counter (Kept images)PSNR (dB): 31.91 -> 27.47Hurt
Flash-Refine vs base model on dropped viewsFlash-Refine · Bicycle (Dropped images)PSNR (dB): 15.19 -> 16.91Improved

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