AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

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

Tsung-Chih Chiang, Hsuan-Kung Yang, Jou-Min Liu, Ting-Ru Liu, Chun-Wei Huang, Quan Kong, Chun-Yi Lee

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 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
use visibility-based view selection instead of random frames (ablation)IVSGround pipeline · NR3D 250-query subsetoverall accuracy: 58.4 -> 64.8Improved
add learned influential view selection (IVS) on top of visibility selection (ablation)IVSGround pipeline · NR3D 250-query subsetoverall accuracy: 64.8 -> 66.0Improved
mix 2 IVS views with 3 visibility views rather than pure heuristic (ablation)IVSGround (k=5) · NR3D 250-query subsetoverall accuracy: 64.8 -> 68.8Improved
use pure IVS (5 views) instead of the hybrid mix (ablation)IVSGround (k=5) · NR3D 250-query subsetoverall accuracy: 68.8 -> 63.6Hurt
add VLM-based verification stage to Cascade Object Screening (ablation)IVSGround COS · NR3D 250-query subsetoverall accuracy: 55.2 -> 58.4Improved
add VLM-based verification stage to Cascade Object Screening (ablation)IVSGround COS · NR3D 250-query subset (Hard)Hard accuracy: 43.9 -> 48.2Improved
plug IVS views into SeqVLM without retraining (ablation)SeqVLM · NR3D 250-query subsetAcc@0.25: 52.0 -> 58.4 (+6.4)Improved
add IVS to Qwen3-VL-32B reasoner (ablation)IVSGround · NR3D 250-query subsetoverall accuracy: 64.8 -> 66.0Improved
add IVS (selector trained on Qwen3-VL-32B feedback) to Qwen2.5-VL-72B reasoner without retraining (ablation)IVSGround · NR3D 250-query subsetoverall accuracy: 55.2 -> 56.8Improved
IVSGround vs SPAZER under shared Qwen2.5-VL-72B reasonerIVSGround · NR3D 250-query subsetAcc@0.25: 57.6 vs 56.0Improved
IVSGround vs SeeGround under shared Qwen2.5-VL-72B reasonerIVSGround · NR3D 250-query subsetAcc@0.25: 57.6 vs 54.0Improved
IVSGround vs SPAZER on ScanRefer VLM-Grounder subsetIVSGround · ScanRefer (VLM-Grounder subset)Acc@0.25 overall: 58.0 vs 57.2Improved

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