AI Paper Atlas

Research map / 3D vision / Depth and stereo

CostDCNet: Cost Volume Based Depth Completion for a Single RGB-D Image

Jaewon Kam, Jungeon Kim, Soongjin Kim, Jaesik Park, Seungyong Lee

ECCV 2022 · 3D vision › Depth and stereo · approach: Cost-volume multi-view stereo · 32 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
replace 2D UNet with tiny 3D UNet on RGB-D feature volume (ablation)CostDCNet · NYUv2 ablation (1/4 resolution, 20 epochs)RMSE (m): 0.195 -> 0.121Improved
use pseudo-3D convolution instead of full 3D convolution (ablation)3D UNet · NYUv2 ablation (1/4 resolution, 20 epochs)RMSE (m): 0.121 -> 0.123No clear effect
add geometric feature volume to image feature volume (ablation)RGB-D volume Type A · NYUv2 ablation (1/4 resolution, 20 epochs)RMSE (m): 0.186 -> 0.123Improved
assign unknown-depth features to all depth planes (Type A vs Type B) (ablation)RGB-D volume · NYUv2 ablation (1/4 resolution, 20 epochs)RMSE (m): 0.131 -> 0.123Improved
assign valid-depth features to correct depth planes (Type C vs Type A) (ablation)RGB-D volume · NYUv2 ablation (1/4 resolution, 20 epochs)RMSE (m): 0.123 -> 0.122Improved
add 2D and 3D encoders (ablation)CostDCNet Type C · NYUv2 ablation (1/4 resolution, 20 epochs)RMSE (m): 0.122 -> 0.108Improved
use bilateral grid learning instead of bilinear upsampling (ablation)CostDCNet · NYUv2 ablation (1/4 resolution, 20 epochs)RMSE (m): 0.106 -> 0.102Improved
use per-plane pixel shuffle instead of bilinear upsampling (ablation)CostDCNet · NYUv2 ablation (1/4 resolution, 20 epochs)RMSE (m): 0.106 -> 0.099Improved
use per-plane pixel shuffle instead of bilateral grid (ablation)CostDCNet · NYUv2 ablation (1/4 resolution, 20 epochs)parameters: 3.1M -> 1.8MImproved
use CostDCNet instead of Huang et al.depth completion · Matterport3D semi-denseRMSE (m): 1.092 -> 1.019Improved
use CostDCNet instead of NLSPN with 500 pointsdepth completion · NYUv2 (500 points)RMSE (m): 0.092 -> 0.096Hurt
use CostDCNet instead of Point-Fusion with 32 pointsdepth completion · NYUv2 (32 points)RMSE (m): 0.319 -> 0.258Improved

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