AI Paper Atlas

Research map / 3D vision / 3D generation

DINO Eats CLIP: Adapting Beyond Knowns for Open-set 3D Object Retrieval

Xinwei He, Yansong Zheng, Qianru Han, Zhichuan Wang, Yuxuan Cai, Yang Zhou, Jingbo Xia, Yulong Wang, Jinhai Xiang, Xiang Bai

CVPR 2026 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 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 Chunking and Adapting Module (CAM) (ablation)DINOv2 ViT-B/14 adapter · OS-MN40-coremAP: 63.49 -> 66.43Improved
add Chunking and Adapting Module (CAM) (ablation)DINOv2 ViT-L/14 adapter · OS-MN40-coremAP: 65.89 -> 68.43Improved
add Virtual Feature Synthesis (VFS) (ablation)DINOv2 ViT-B/14 + CAM · OS-MN40-coremAP: 66.43 -> 67.62Improved
add Virtual Feature Synthesis (VFS) (ablation)DINOv2 ViT-L/14 + CAM · OS-MN40-coremAP: 68.43 -> 69.69Improved
use CAM instead of CLIP-Adaptor (ablation)DINOv2 ViT-B/14 · OS-MN40-coremAP: 64.35 -> 66.43Improved
use chunk size 3 instead of 1 (ablation)CAM · OS-MN40-coremAP: 63.62 -> 67.62Improved
use chunk size 3 instead of 5 (ablation)CAM · OS-MN40-coremAP: 64.91 -> 67.62Improved
use chunk size 3 instead of 7 (ablation)CAM · OS-MN40-coremAP: 65.72 -> 67.62Improved
use non-overlapping stride 3 instead of stride 1 (ablation)CAM · OS-MN40-coremAP: 64.64 -> 67.62Improved
use non-overlapping stride 3 instead of stride 2 (ablation)CAM · OS-MN40-coremAP: 65.52 -> 67.62Improved
naively fuse CLIP features with DINOv2 instead of using CLIP only for VFS (ablation)DINOv2 baseline · OS-MN40-coremAP: 62.77 -> 61.35Hurt
raise fusion weight lambda beyond about 0.4 (ablation)CAM residual fusion · OS-MN40-coremAPMixed

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