AI Paper Atlas

Research map / 3D vision / Depth and stereo

PacGDC: Label-Efficient Generalizable Depth Completion with Projection Ambiguity and Consistency

Haotian Wang, Aoran Xiao, Xiaoqin Zhang, Meng Yang, Shijian Lu

ICCV 2025 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 4 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 DepthAnything pseudo depth labels (ablation)SPNet-Tiny · Ablation 25% dataRMSE (mm): 2484 -> 2463Improved
raise interpolation probability from 0.0 to 1.0 (ablation)SPNet-Tiny · Ablation 25% dataRMSE (mm): 2463 -> 2330Improved
add relocation of interpolated labels (ablation)SPNet-Tiny · Ablation 25% dataRMSE (mm): 2330 -> 2277Improved
add DepthPro as second foundation model (ablation)SPNet-Tiny · Ablation 25% dataRMSE (mm): 2277 -> 2241Improved
add 390K unlabeled SA1B images (ablation)SPNet-Tiny · Ablation 25% dataRMSE (mm): 2241 -> 2143Improved
apply full PacGDC synthesis to SPNet-Tiny (ablation)SPNet-Tiny · Ablation 25% dataMAE (mm): 990 -> 792Improved
apply full PacGDC synthesis to G2-MonoDepth (ablation)G2-MonoDepth · Ablation 25% dataRMSE (mm): 2669 -> 2192Improved
add DistillAnyDepth to DA+DepthPro+DAV2 foundation model set (ablation)SPNet-Tiny · Ablation 25% dataRMSE (mm): 2232 -> 2279Hurt
add DAV2 to DA+DepthPro foundation model set (ablation)SPNet-Tiny · Ablation 25% dataRMSE (mm): 2241 -> 2232Improved
PacGDC synthesis vs SPNet baseline on uniform sparse depth zero-shot (Large)SPNet-Large · Zero-shot uniform meanRMSE (mm): 2271 -> 1966Improved
PacGDC pretrained weights for few-shot fine-tuning vs best baseline (1 sample)PacGDC · KITTI 64-line few-shot, 1 sampleRMSE (mm): 1358 -> 1078Improved
3x3 instead of 2x2 convolution in SPNet up/down samplingSPNet · inference costspeed (image/s): 126.6 -> 121.8Hurt

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