AI Paper Atlas

Research map / 3D vision / Depth and stereo

BiFuse++: Self-Supervised and Efficient Bi-Projection Fusion for $360^{\circ }$ Depth Estimation

Fu-En Wang, Yu-Hsuan Yeh, Yi-Hsuan Tsai, Wei-Chen Chiu, Min Sun

TPAMI 2022 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 43 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
use BiFuse++ instead of BiFusedepth fusion · Matterport3DMAE: 0.3470 -> 0.2842Improved
use BiFuse++ instead of HoHoNetdepth estimation · Matterport3DMAE: 0.2862 -> 0.2842No clear effect
use BiFuse++ instead of HoHoNetdepth estimation · Stanford2D3DMAE: 0.2027 -> 0.2173Hurt
use BiFuse++ instead of UniFusedepth estimation · PanoSUNCG (supervised)MAE: 0.0776 -> 0.0688Improved
use BiFuse++ instead of HoHoNet under rotation noisedepth estimation · Matterport3D (rotation noise)MAE: 0.3085 -> 0.3054Improved
use BiFuse++ instead of HoHoNet under rotation noisedepth estimation · Stanford2D3D (rotation noise)MAE: 0.2210 -> 0.2193Improved
use new fusion module instead of BiFuse modulefusion module · fusion module parametersparameters: 4.7 M -> 2.1 MImproved
use BiFuse++ instead of BiFusefull network · GFLOPs / runtime memoryGFLOPs: 682.86 -> 87.42 GFLOPs; 3346 -> 1762 MbImproved
add contrast-aware photometric loss (CAPL) instead of SPL (ablation)BiFuse++ · PanoSUNCG (self-supervised)RMSE: 0.4695 -> 0.4321Improved
use SPL instead of SSIM photometric loss (ablation)BiFuse++ · PanoSUNCG (self-supervised)RMSE: 0.5889 -> 0.4695Improved
use BiFuse++ w/ CAPL instead of 360-SelfNetself-supervised depth · PanoSUNCG (self-supervised)RMSE: 0.5121 -> 0.4321Improved
use BiFuse++ w/ CAPL instead of UniFuseself-supervised depth · PanoSUNCG (self-supervised)MAE: 0.2452 -> 0.1815Improved

Later papers that compared with this method

5 later accepted papers report Bifusev2 as a baseline in their results tables; 5 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