AI Paper Atlas

Research map / 3D vision / Depth and stereo

Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model

Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys

TPAMI 2025 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo

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 diffusion model refinement (ablation)DiffMVS · DTU testOverall (mm): 0.318 -> 0.308Improved
add diffusion model refinement (ablation)DiffMVS · ETH3D trainingF1-score: 70.69 -> 74.86Improved
add noise only in training (ablation)DiffMVS · DTU testOverall (mm): 0.318 -> 0.329Hurt
add cost volume as diffusion condition (ablation)DiffMVS · DTU testOverall (mm): 2.682 -> 0.308Improved
add depth context as diffusion condition (ablation)DiffMVS · ETH3D trainingF1-score: 43.07 -> 74.86Improved
add image context as diffusion condition (ablation)DiffMVS · DTU testOverall (mm): 0.311 -> 0.308Improved
use multiple samples with confidence-based sampling instead of a single sample (ablation)DiffMVS · ETH3D trainingF1-score: 66.77 -> 74.86Improved
add confidence-based sampling instead of no confidence (ablation)DiffMVS · DTU testOverall (mm): 0.319 -> 0.308Improved
use confidence for sampling rather than only regularization (ablation)DiffMVS · ETH3D trainingF1-score: 73.22 -> 74.86Improved
use GRU instead of stacked U-Nets (ablation)DiffMVS · ETH3D trainingF1-score: 71.93 -> 74.86Improved
use GRU instead of single U-Net (ablation)DiffMVS · DTU testOverall (mm): 2.317 -> 0.308Improved
increase DDIM sampling steps from 1 to 2 (ablation)DiffMVS · DTU testDepth error (mm): 4.68 -> 4.63No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 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