AI Paper Atlas

Research map / 3D vision / Depth and stereo

OGNI-DC: Robust Depth Completion with Optimization-Guided Neural Iterations

Yiming Zuo, Jia Deng

ECCV 2024 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 26 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 DDI (differentiable depth integrator) over directly regressing depth (ablation)OGNI-DC · NYUv2 val (500 points)RMSE (mm): 128.6 -> 112.2Improved
add DDI (ablation)OGNI-DC · VOID500 val subset (cross-dataset)MAE (mm): 237.9 -> 229.0Improved
unroll ConvGRU 5 iterations instead of 1 (ablation)OGNI-DC · NYUv2 val (500 points)MAE (mm): 39.9 -> 38.0Improved
unroll 7 GRU iterations instead of 5 (ablation)OGNI-DC · NYUv2 val (500 points)MAE (mm): 38.0 -> 38.0No clear effect
7 GRU iterations instead of 5, tested on VOID (ablation)OGNI-DC · VOID500 val subsetMAE (mm): 229.0 -> 257.5Hurt
add random masking of sparse depth during training (ablation)OGNI-DC · NYUv2 val (100 points)RMSE (mm): 292.3 -> 171.5Improved
add random masking of sparse depth during training (ablation)OGNI-DC · NYUv2 val (500 points)RMSE (mm): 110.1 -> 112.2Hurt
add sparse depth as backbone input (RGBD vs RGB backbone) (ablation)OGNI-DC · NYUv2 val (500 points)RMSE (mm): 121.3 -> 112.2Improved
add DySPN on top of the output (ablation)OGNI-DC · NYUv2 val (10000 points)RMSE (mm): 68.1 -> 53.0Improved
use NLSPN instead of DySPN (ablation)OGNI-DC · VOID500 val subsetMAE (mm): 229.0 -> 286.0Hurt
add supervision on upsampled depth (ablation)OGNI-DC · VOID500 val subsetMAE (mm): 252.8 -> 229.0Improved
add depth gradient supervision (ablation)OGNI-DC · VOID500 val subsetMAE (mm): 252.2 -> 229.0Improved

Later papers that compared with this method

4 later accepted papers report OGNI-DC as a baseline in their results tables; 4 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