paper-with-me

3D Object Retrieval

2개 벤치마크 · 논문 31편 · 이 태스크의 논문 보기 →

Benchmarks

ModelNet40

결과 1개

ShapeNetCore 55

결과 1개

Most implemented

Papers

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

2026-04-21 · Xinwei He, Yansong Zheng, Qianru Han, Zhichuan Wang 외 arxiv

Vision foundation models have shown great promise for open-set 3D object retrieval (3DOR) through efficient adaptation to multi-view images. Leveraging semantically aligned latent space, previous work typically adapts th…

3D Object Retrieval

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

2025-07-29 · Zhichuan Wang, Yang Zhou, Zhe Liu, Rui Yu 외 arxiv

Open-set 3D object retrieval (3DOR) is an emerging task aiming to retrieve 3D objects of unseen categories beyond the training set. Existing methods typically utilize all modalities (i.e., voxels, point clouds, multi-vie…

3D Object RetrievalPoint Clouds

SAMURAI: Shape-Aware Multimodal Retrieval for 3D Object Identification

2025-06-26 · Dinh-Khoi Vo, Van-Loc Nguyen, Minh-Triet Tran, Trung-Nghia Le

Retrieving 3D objects in complex indoor environments using only a masked 2D image and a natural language description presents significant challenges. The ROOMELSA challenge limits access to full 3D scene context, complic…

3D Object RetrievalObjectRe-RankingRetrieval

TeDA: Boosting Vision-Lanuage Models for Zero-Shot 3D Object Retrieval via Testing-time Distribution Alignment

2025-05-05 · Zhichuan Wang, Yang Zhou, Jinhai Xiang, Yulong Wang 외

Learning discriminative 3D representations that generalize well to unknown testing categories is an emerging requirement for many real-world 3D applications. Existing well-established methods often struggle to attain thi…

3D Object RetrievalLanguage ModelingLanguage ModellingRetrieval+2

Segment then Splat: A Unified Approach for 3D Open-Vocabulary Segmentation based on Gaussian Splatting

2025-03-28 · Yiren Lu, Yunlai Zhou, Yiran Qiao, Chaoda Song 외

Open-vocabulary querying in 3D space is crucial for enabling more intelligent perception in applications such as robotics, autonomous systems, and augmented reality. However, most existing methods rely on 2D pixel-level …

3D Object RetrievalObjectSegmentation

Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graph

2024-06-11 · Sergey Linok, Tatiana Zemskova, Svetlana Ladanova, Roman Titkov 외

Locating objects described in natural language presents a significant challenge for autonomous agents. Existing CLIP-based open-vocabulary methods successfully perform 3D object grounding with simple (bare) queries, but …

3D Object Retrieval3D Semantic SegmentationLanguage ModelingLanguage Modelling+3

전체 31편 보기 →