AI Paper Atlas

Research map / 3D vision / Depth and stereo

Deep Cost Ray Fusion for Sparse Depth Video Completion

Jungeon Kim, Soongjin Kim, Jaesik Park, Seungyong Lee

ECCV 2024 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 1 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 ray-based cost volume fusion (self+cross attention) (ablation)RayFusion base network · KITTI val (20% train)MAE (mm): 203.05 -> 198.51Improved
use convolutional GRU local fusion instead of ray-based fusion (ablation)RayFusion · KITTI val (20% train)MAE (mm): 215.18 -> 228.85Hurt
add L1 depth loss to cross-entropy loss (ablation)RayFusion base network · KITTI val (20% train)MAE (mm): 223.59 -> 203.05Improved
add L2 loss to CE + L1 (ablation)RayFusion base network · KITTI val (20% train)MAE (mm): 203.05 -> 220.22Hurt
add NLSPN-based depth refinement module (ablation)RayFusion · KITTI valMAE (mm): 182.65 -> 176.23Improved
add NLSPN-based depth refinement module (ablation)RayFusion · ScanNetV2 testMAE (m): 0.0159 -> 0.0160No clear effect
add NLSPN-based depth refinement module (ablation)RayFusion · VOID test (0.5%)MAE (mm): 24.57 -> 24.51No clear effect
add temporal cross-attention fusion vs single-view setting (ablation)RayFusion · ScanNetV2 testMAE (m): 0.0208 -> 0.0159Improved
ray-based cost volume fusion vs prior methods on unseen sparsityRayFusion · VOID (train 0.5%, test 0.05%)MAE (mm): 104.97 -> 78.55Improved
RayFusion cross-dataset transfer vs CompletionFormerRayFusion · ScanNetV2 train -> VOID testMAE (mm): 65.90 -> 29.08Improved
use soft labels instead of one-hot for cost volume supervision (ablation)RayFusion · depth completionperformanceImproved

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