AI Paper Atlas

Research map / 3D vision / 3D generation

Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval

Zhichuan Wang, Yang Zhou, Zhe Liu, Rui Yu, Song Bai, Yulong Wang, Xinwei He, Xiang Bai

ICCV 2025 · 3D vision › 3D generation · approach: Learning 3D reconstruction from images · 4 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 InternVL descriptions at inference (ablation)DAC (CLIP ViT-B/32) · OS-ABO-coremAP: +9.65% mAPImproved
add InternVL descriptions at inference (ablation)DAC (CLIP ViT-B/32) · OS-ESB-coremAP: 57.45 -> 58.70Improved
add AB-LoRA adaptation (ablation)DAC · OS-MN40-coremAP: +7.01% mAP (ViT-B/32), +9.21% (ViT-L/14)Improved
add additive bias to LoRA (ablation)DAC (CLIP ViT-B/32) · OS-MN40-coremAP: 59.85 -> 62.40Improved
add LoRA adaptation to CLIP (ablation)DAC (CLIP ViT-B/32) · OS-MN40-coremAP: 55.39 -> 59.85Improved
fuse by addition instead of concatenation (ablation)DAC (CLIP ViT-B/32) · OS-MN40-coremAP: 55.30 -> 62.40Improved
fuse by addition instead of concatenation (ablation)DAC (CLIP ViT-L/14) · OS-MN40-coremAP: 56.74 -> 68.98Improved
raise LoRA rank from 8 to 12 (ablation)DAC · OS-MN40-coremAP: 62.40 -> 62.17No clear effect
add Tanh normalization after fusion (ablation)DAC (CLIP ViT-B/32) · OS-ABO-coremAP: 64.63 -> 66.10Improved
use ReLU after fusion (ablation)DAC (CLIP ViT-B/32) · OS-ABO-coremAP: 64.63 -> 63.13Hurt
train with InternVL category descriptions instead of hand-crafted template (text fusion at retrieval) (ablation)DAC (CLIP ViT-B/32) · OS-ABO-coremAP gain from text: +9.06 -> +9.65Improved
use category-level instead of individual-level descriptions (ablation)DAC (CLIP ViT-B/32) · OS-ESB-coremAP: 48.78 -> 58.70Improved

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