AI Paper Atlas

Research map / 3D vision / Gaussian splatting

Enhancing Embodied Reasoning and Grounding by Novel View Synthesis

Yu-Ji Kim, Dahye Lee, Kim Jun-Seong, Nam Hyeon-Woo, GeonU Kim, Yongjin Kwon, Yu-Chiang Frank Wang, Jaesung Choe, Tae-Hyun Oh

ECCV 2026 · 3D vision › Gaussian splatting · approach: Sparse-view Gaussian splatting for novel views

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 score instead of 3D-Mem view selection (ablation)SplatReasoner · EM-EQA 184 subsetLLM-Match: 45.4 -> 48.2Improved
use visibility score instead of volume score (ablation)SplatReasoner · EM-EQA 184 subsetLLM-Match: 47.8 -> 48.2Improved
add novel view synthesis and final view selection (ablation)SplatReasoner · EM-EQA 184 subsetLLM-Match: 48.2 -> 50.5Improved
use text-based LLM judge instead of image-based VLM judge (ablation)SplatReasoner · EM-EQA 184 subsetLLM-Match: 47.1 -> 50.5Improved
use text-only judge instead of image+text (ablation)SplatReasoner · EM-EQA 184 subsetLLM-Match: 46.9 -> 50.5Improved
add verification stage (ablation)SplatReasoner · EM-EQA 1,623LLM-Match: 54.5 -> 57.8Improved
SplatReasoner vs 3D-Mem (GPT-4o)SplatReasoner · EM-EQALLM-Match: 54.6 -> 57.8Improved
SplatReasoner vs 3D-Mem (Qwen3-VL-8B)SplatReasoner · EM-EQALLM-Match: 50.8 -> 51.6Improved
SplatReasoner vs Dr. Splat (sentence) on referring segmentation Acc@8SplatReasoner · 3D referring segmentationAcc@8: 45.21 vs 45.14No clear effect
SplatReasoner vs Dr. Splat (category) on Multi3DReferSplatReasoner · Multi3DReferAcc@8: 18.33 -> 29.59Improved
ReferSplat vs others on groundingReferSplat · ScanRefer3D mIoU: 3.14 vs 9.44 (Dr. Splat sentence)Hurt

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