← Back to all news
arXiv Computer Vision By Tsung-Chih Chiang, Hsuan-Kung Yang, Jou-Min Liu, Ting-Ru Liu, Chun-Wei Huang, Quan Kong, Chun-Yi Lee

Where to Look Matters: Learning Influential Views for VLM-based 3D Visual Grounding

Read the original on arXiv Computer Vision →

IVSGround introduces a lightweight view selector that learns to choose the most informative camera views for vision‑language model (VLM) based 3D visual grounding, replacing heuristic view selection. The selector is trained via a two‑stage rejection sampling process that uses feedback from a reasoning VLM to generate supervision signals. Experiments on ScanRefer and NR3D demonstrate that IVSGround consistently improves grounding accuracy over existing zero‑shot pipelines, underscoring the importance of selecting where to look for effective 3D visual grounding.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv Computer Vision
Oct 9

Seek-and-View Reasoning for Multi-View Spatial Understanding

The paper introduces Vantage, a training‑free, model‑agnostic framework that pairs a vision‑language model with a 3D foundation model to perform Seek‑and‑View reasoning for multi‑view spatial understanding. Vantage first analyzes a question to plan a relevant viewpoint, then augments reasoning with geometry‑grounded visual evidence from that viewpoint. Experiments across six VLMs on five benchmarks show consistent improvements without fine‑tuning, demonstrating that revealing spatial evidence through view‑grounded reasoning reduces reliance on language‑based cross‑view alignment.

By Qixiang Chen, Cheng Zhang, Fucai Ke, Chi-Wing Fu, Jianfei Cai, Jingwen Ye
llmsfine-tuningmultimodalbenchmarkssafety
More like this →