AI Paper Atlas

Research map / 3D vision / Depth and stereo

PixVOD: Pixel-Distributed Direct Visual Odometry and Depth Estimation

Shinjeong Kim, Ignacio Alzugaray, Callum Rhodes, Paul Kelly, Andrew Davison

ECCV 2026 · 3D vision › Depth and stereo · approach: Depth from light field and defocus · 0 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
use hierarchical quad-tree identity factors instead of grid (ablation)PixVOD · ReplicaGBP iterations / FLOPs: 1711 FLOPs/px vs 1135 FLOPs/px; grid needs at least 50 times more GBP iterationsImproved
add photometric factors to normal integration (vs BINI alone)PixVOD · Replica depthdepth qualityImproved
use DSINE normals instead of ground-truth normals (ablation)PixVOD · Replicapose error: 7.29 -> 7.21 RPE-r; 91.3 -> 99.3 RPE-t; 97 -> 93 successMixed
use ground-truth depth prior instead of estimated normals (ablation)PixVOD · ReplicaconvergenceImproved
use keyframe tracking with frequent target updates (framerate 10 instead of 0.2) (ablation)PixVOD · Replicarelative pose errorImproved
increase target-frame update rate from framerate 5 to 10 (ablation)PixVOD · Replicarelative pose errorNo clear effect
use mild photometric noise (ablation)PixVOD · Replica with noiseconvergence basinHurt
use half image resolution (ablation)PixVOD · Replicapose errorNo clear effect
use quarter image resolution (ablation)PixVOD · Replicapose errorHurt
use too weak or too strong camera motion identity factor (ablation)PixVOD · Replicapose errorHurt
use identical factor strengths across layers instead of halving per layer (ablation)PixVOD · ReplicaconvergenceImproved
use larger numbers of iterations per frame (ablation)PixVOD · Replicapose accuracyImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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