AI Paper Atlas

Research map / 3D vision / Depth and stereo

AA-RMVSNet: Adaptive Aggregation Recurrent Multi-View Stereo Network

Zizhuang Wei, Qingtian Zhu, Chen Min, Yisong Chen, Guoping Wang

ICCV 2021 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 216 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 intra-view adaptive aggregation (deformable multi-scale features) to the baseline (ablation)AA-RMVSNet baseline · DTU evaluation setoverall error (mm): 0.391 -> 0.371Improved
add intra-view adaptive aggregation to the baseline (ablation)AA-RMVSNet baseline · DTU evaluation setcompleteness error (mm): 0.374 -> 0.346Improved
add intra-view adaptive aggregation to the baseline (ablation)AA-RMVSNet baseline · DTU evaluation setmemory (GB): 2.41 -> 4.15Hurt
add inter-view adaptive aggregation to the baseline (ablation)AA-RMVSNet baseline · DTU evaluation setoverall error (mm): 0.391 -> 0.370Improved
add inter-view adaptive aggregation to the baseline (ablation)AA-RMVSNet baseline · DTU evaluation setaccuracy error (mm): 0.408 -> 0.377Improved
add inter-view adaptive aggregation to the baseline (ablation)AA-RMVSNet baseline · DTU evaluation setmemory (GB): 2.41 -> 2.52No clear effect
combine both intra-view and inter-view aggregation modules (ablation)AA-RMVSNet baseline · DTU evaluation setoverall error (mm): 0.391 -> 0.357Improved
increase number of input views N from 3 to 7 (ablation)AA-RMVSNet · DTU evaluation setoverall error (mm): 0.405 -> 0.386 -> 0.380Improved
increase depth hypotheses D from 256 to 512 (ablation)AA-RMVSNet · DTU evaluation setoverall error (mm): 0.380 -> 0.372Improved
increase input resolution from 480x360 to 800x600 (ablation)AA-RMVSNet · DTU evaluation setoverall error (mm): 0.372 -> 0.366 -> 0.357Improved
use recurrent cost regularization with adaptive aggregation instead of 3D CNN (vs MVSNet)AA-RMVSNet · DTU evaluation setmemory (GB): 15.4 -> 4.25Improved

Later papers that compared with this method

4 later accepted papers report AA-RMVSNet as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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