arXiv Computer Vision November 9, 2026 By Fan Zhu, Rui Yu

BEV3SR: Evidence-Aware 3D Spatial Reasoning from Video

Read the original on arXiv Computer Vision →

BEV3SR is a training‑free, backbone‑agnostic framework that converts RGB‑D video observations into a queryable metric bird’s‑eye‑view (BEV) scene memory, enabling evidence‑aware 3D spatial reasoning. It formalizes each query into a spatial task specifying reference frame, constraints, objective, and evidence type, then routes the query to either a deterministic Geometric Reasoner or a Visual Evidence Aligner. Across multiple 3D scene QA benchmarks, BEV3SR consistently improves performance on spatially intensive and open‑ended questions within a 16‑frame budget.

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.

arXiv Computer Vision

Oct 21

Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning with Lightweight Annotations

arXiv:2506.17545v2 Announce Type: replace Abstract: Large language models are increasingly being applied to 3D scene understanding. However, existing 3D-aware LLMs largely operate as black boxes: the...

By Junjie Wang, Zhihao Yuan, Shuyi Jiang, Chun-Mei Feng, Yaolun Zhang, Shuguang Cui, Zhen Li, Na Zhao

llms computer-vision nlp

arXiv AI

Jun 11

Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning

arXiv:2606. 11683v1 Announce Type: cross Abstract: Spatial reasoning from egocentric videos is inherently challenging because the observable evidence is constrained by the camera trajectory.

By Chaofan Ma, Zhenjie Mao, Yuhuan Yang, Fanqin Zeng, Yue Shi, Yingjie Zhou, Xiaofeng Cao, Jiangchao Yao

benchmarks

arXiv AI

Jul 7

R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables

arXiv:2607. 02921v1 Announce Type: cross Abstract: Quantitative 3D spatial reasoning from egocentric RGB-D video is a critical capability for next-generation wearable assistants.

By Maxwell Horton, Wei Lu, Quan Tran, Yury Astashonok, Kirmani Ahmed, Babak Damavandi, Anuj Kumar, Xiao Zhang, Seungwhan Moon

llms computer-vision benchmarks

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

llms fine-tuning multimodal benchmarks safety

arXiv AI

Jun 15

3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding

arXiv:2603. 04976v2 Announce Type: replace-cross Abstract: Reinforcement Learning with Verifiable Rewards ( RLVR ) has emerged as a transformative paradigm for enhancing the reasoning capabilities of Large Language Models ( LLMs), yet its potential in 3D scene understanding remains under-explored.

By Xiongkun Linghu, Jiangyong Huang, Baoxiong Jia, Siyuan Huang

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv Computer Vision

Oct 27

GeoLift: Grounding Video Spatial Reasoning in Explicit 3D Maps

arXiv:2610.33558v1 Announce Type: new Abstract: Video spatial reasoning requires multimodal large language models (MLLMs) to understand how objects are arranged and related across viewpoints. While t...

By Xinglin Li, TingTing Long, Jingzhi Zhou, Jiajing Chen, Jian Yang, Jin Xie

llms multimodal

One email a morning, machine-written

Related stories

Scene-R1: Video-Grounded Large Language Models for 3D Scene Reasoning with Lightweight Annotations

Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning

R3D: Quantitative 3D Spatial Reasoning for Egocentric Wearables

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

3D-RFT: Reinforcement Fine-Tuning for Video-based 3D Scene Understanding

GeoLift: Grounding Video Spatial Reasoning in Explicit 3D Maps