AI Paper Atlas

Research map / 3D vision / Gaussian splatting

I2-SLAM: Inverting Imaging Process for Robust Photorealistic Dense SLAM

Gwangtak Bae, Changwoon Choi, Hyeongjun Heo, Sang Min Kim, Young Min Kim

ECCV 2024 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction

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 tone mapping (HDR image formation) to the SLAM pipeline (ablation)I2-SLAM on ScanNet · ScanNet ablationPSNR: 22.39 -> 25.62Improved
add trajectory regularization (ablation)I2-SLAM on ScanNet · ScanNet ablationPSNR: 24.80 -> 25.62Improved
add trajectory regularization (ablation)I2-SLAM on ScanNet · ScanNet ablationATE (cm): 2.66 -> 2.56Improved
add motion-blur-aware rendering (ablation)I2-SLAM on ScanNet · ScanNet ablationATE (cm): 2.71 -> 2.63Improved
add motion blur modeling without tone mapping (ablation)I2-SLAM on ScanNet · ScanNet ablationPSNR: 23.05 -> 22.36Hurt
attach I2-SLAM to NeRF-SLAM re-implementationNeRF-SLAM · TUM-RGBD fr3/officeATE RMSE (cm): 7.13 -> 1.95Improved
attach I2-SLAM to SplaTAM for trackingSplaTAM · ScanNet and synthetic RGBDATE RMSE (cm): 5.91 -> 4.59Mixed
attach I2-SLAM to SplaTAM for rendering on scenes with changing appearanceSplaTAM · ScanNet 0785-00PSNR: 19.63 -> 26.40Improved
pre-deblur inputs with NAFNet before NeRF-SLAM instead of modeling blur physically (ablation)NeRF-SLAM · TUM-RGBDPSNR: 26.89 -> 26.61No clear effect
run I2-SLAM with 20% iterations (I2-SLAM-S) versus SplaTAM-SSplaTAM · ScanNet 0024-01PSNR: 21.43 -> 23.92Improved
increase the number of virtual cameras for motion blur simulation (ablation)I2-SLAM RGB · Synthetic Italian-flat-1PSNRImproved
attach I2-SLAM to SplaTAMSplaTAM · ScanNet 0736-00PSNR: 24.50 -> 24.07Hurt

Later papers that compared with this method

1 later accepted paper reports I2-SLAM as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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