AI Paper Atlas

Research map / 3D vision / Depth and stereo

Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering

Chi Zhang, Wei Yin, Gang Yu, Zhibin Wang, Tao Chen, Bin Fu, Joey Tianyi Zhou, Chunhua Shen

ICCV 2023 · 3D vision › Depth and stereo · approach: Self-supervised monocular depth · 7 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 multi-view rendering consistency losses to SSI trainingDPT with SSI loss · NYU/ScanNet/ETH3D/KITTI (scale alignment)AbsRel: 27.9 -> 10.5 (NYU), 21.0 -> 12.9 (KITTI)Improved
add the consistency losses on top of GP2GP2 · ETH3D (scale alignment)AbsRel: 14.0 -> 10.9Improved
add multi-focal-length (MFL) loss (ablation)consistency-loss training · mean of 4 benchmarksAbsRel: 13.3 -> 11.7Improved
add depth consistency loss (ablation)consistency-loss training · mean of 4 benchmarksAbsRel: 13.4 -> 11.7Improved
add image consistency loss (ablation)consistency-loss training · mean of 4 benchmarksAbsRel: 12.2 -> 11.7Improved
use depth consistency instead of image consistency to select FOV (ablation)RenderFOV · KITTI point cloudRMSE: 5.95 -> 3.04Improved
use RenderFOV depth-consistency FOV selection instead of PCMpoint cloud reconstruction · KITTI point cloudRMSE: 7.05 -> 3.04Improved
use RenderFOV with image consistency loss instead of PCM (ablation)point cloud reconstruction · 2D3D and NYU point cloudRMSE: 0.67 -> 0.72 (2D3D), 0.38 -> 0.43 (NYU)Hurt
learn affine coefficients self-supervised with consistency losses on unlabeled domain imagesSSI-trained model · KITTIAbsRel: 21.0 -> 13.1 (vs SA); 14.0 with SSAImproved
scale-only aligned geometry-preserving model vs prior SOTA with scale-and-shift alignmentOurs (SA) · ETH3D zero-shotAbsRel: 17.1 -> 9.1Improved

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