AI Paper Atlas

Research map / 3D vision / Depth and stereo

2K Retrofit: Entropy-Guided Efficient Sparse Refinement for High-Resolution 3D Geometry Prediction

Tianbao Zhang, Zhenyu Liang, Zhenbo Song, Nana Wang, Xiaomei Zhang, Xudong Cai, Zheng Zhu, Kejian Wu, Gang Wang, Zhaoxin Fan

ECCV 2026 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 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
select pixels by entropy instead of randomly (ablation)2K Retrofit · ETH3D point mapAccuracy error: 1.126 -> 0.935Improved
use entropy selector instead of edge-based heuristics (ablation)2K Retrofit · ETH3D point mapAccuracy error: 0.942 -> 0.935Improved
use learnable selector instead of entropy selector (ablation)2K Retrofit · ETH3D point mapFPS: 5.5 -> 3.8Hurt
use gated fusion instead of direct replacement (ablation)2K Retrofit · ETH3D point mapAccuracy error: 1.113 -> 0.935Improved
use gated fusion instead of entropy-based fusion (ablation)2K Retrofit · ETH3D point mapAccuracy error: 0.940 -> 0.935Improved
lower entropy threshold alpha from 0.3 to 0.1 (ablation)2K Retrofit · ETH3D point mapAccuracy error / FPS: Acc 0.935 -> 0.917; FPS 5.5 -> 3.4Mixed
raise entropy threshold alpha from 0.3 to 0.8 (ablation)2K Retrofit · ETH3D point mapAccuracy error / FPS: Acc 0.935 -> 1.135; FPS 5.5 -> 8.0Mixed
use Point Transformer instead of MinkowskiUNet as sparse extractor (ablation)2K Retrofit · ETH3D point mapAccuracy error / FPS: Acc 0.935 -> 0.919; FPS 5.5 -> 1.7Mixed
use 2K Retrofit instead of retraining VGGT at 2KVGGT · ETH3D point mapAccuracy error: 0.911 -> 0.935Hurt
use 2K Retrofit instead of retraining VGGT at 2KVGGT · ETH3D point mapGFLOPs: 495 -> 172Improved
add 2K Retrofit sparse refinement to VGGTVGGT · ETH3D point mapOverall error: 0.903 -> 0.839Improved
use 2K Retrofit instead of PRO for monocular depthPRO · ETH3D monocular 2K depthAbsRel: 0.0217 -> 0.0192Improved

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