AI Paper Atlas

Research map / 3D vision / Depth and stereo

InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields

Hao Yu, Haotong Lin, Jiawei Wang, Jiaxin Li, Yida Wang, Xueyang Zhang, Yue Wang, Xiaowei Zhou, Ruizhen Hu, Sida Peng

CVPR 2026 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 16 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
represent depth as neural implicit field instead of DPT grid decoder (ablation)InfiniDepth (metric) · Synth4K-1delta0.01 accuracy: 62.4 -> 72.7Improved
represent depth as neural implicit field instead of DPT grid decoder (ablation)InfiniDepth (metric) · KITTIdelta0.01 accuracy: 49.0 -> 61.7Improved
represent depth as neural implicit field for RGB-only relative depth (ablation)InfiniDepth (relative) · relative depth benchmarksdelta1 accuracyImproved
add multi-scale feature query (ablation)InfiniDepth (metric) · Synth4K-1delta0.01 accuracy: 66.6 -> 72.7Improved
add multi-scale feature query (ablation)InfiniDepth (metric) · ETH3Ddelta0.01 accuracy: 88.7 -> 93.9Improved
use DINOv3 encoder instead of DINOv2 (ablation)InfiniDepth (metric) · Synth4K-1delta0.01 accuracy: 63.8 -> 72.7Improved
use DINOv3 encoder instead of DINOv2 (ablation)InfiniDepth (metric) · ETH3Ddelta0.01 accuracy: 90.1 -> 93.9Improved
InfiniDepth relative model vs MoGe-2zero-shot relative depth · real-world benchmarks (KITTI, NYUv2, ScanNet)delta1 accuracy: KITTI 97.9 vs 98.3No clear effect
query implicit field at native 4K instead of upsampling baseline outputsrelative depth · Synth4K-1delta1 accuracy: 84.2 -> 89.0Improved
InfiniDepth Ours-Metric instead of PromptDAsparse-depth metric estimation · Synth4K-1 high-frequency regionsdelta0.01 accuracy: 21.1 -> 33.2Improved
InfiniDepth Ours-Metric instead of PromptDAsparse-depth metric estimation · KITTIdelta0.01 accuracy: 58.3 -> 63.9Improved
add infinite depth query for uniform 3D pointssingle-view novel view synthesis · large viewpoint shifts (qualitative)holes and artifactsImproved

Later papers that compared with this method

1 later accepted paper reports InfiniDepth as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

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