AI Paper Atlas

Research map / 3D vision / 3D generation

DINOv3D: 2D-3D Joint Optimization for Unified Spatial Understanding

Bo Zhou, Jianzhe Gao, Zhihui Wang, Lingxiang Wu, Jinqiao Wang, Yazhou Yao, Wenguan Wang

ECCV 2026 · 3D vision › 3D generation · approach: Semantic scene completion · 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
add dual-branch teacher-student architecture to frozen baseline (ablation)Frozen baseline · ScanNetPSNR: 23.45 -> 24.62Improved
add dual-branch architecture (ablation)Frozen baseline · ADE20kmIoU: 54.9 -> 55.0No clear effect
add ray-depth-semantic alignment (ablation)Dual-branch model · ScanNetPSNR: 24.62 -> 25.41Improved
add ray-depth-semantic alignment (ablation)Dual-branch model · ScanNetOVSS mIoU: 54.5 -> 55.6Improved
add long context (128 frames) (ablation)Dual-branch + alignment · ScanNetPSNR: 25.41 -> 25.58Improved
train on Uni3D dataset (ablation)Full pipeline · ScanNetmIoU: 56.5 -> 57.7Improved
extend context length from 8 to 128 frames (ablation)DINOv3D · ScanNetPSNR: 24.62 -> 25.67Improved
extend context length from 128 to 144 frames (ablation)DINOv3D · ScanNetPSNR: 25.67 -> 25.69No clear effect
use LoRA instead of frozen backbone (ablation)DINOv3D · ScanNetPSNR: 24.15 -> 25.67Improved
use LoRA instead of full fine-tuning (ablation)DINOv3D · NYUv2RMSE: 0.385 -> 0.324Improved
use LoRA instead of full fine-tuning (ablation)DINOv3D · ScanNetPSNR: 25.72 -> 25.67No clear effect
use LoRA instead of full fine-tuning (ablation)DINOv3D · NYUv2mAcc: 77.5 -> 84.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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