arXiv Computer Vision
LeRF: Learning Reference Coordinate Frames for Perspective Taking Reasoning
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv AI
Sep 10
MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability Modeling
MV-STRIDE is a Multi‑View hierarchical Spatial Reasoning dataset that models dependencies among perception, scene understanding, and contextual reasoning to support 3D spatial cognition. It introduces a QA generation pipeline that enforces cross‑view constraints, producing multi‑level reasoning tasks with chain‑of‑thought supervision. Experiments show that training on MV‑STRIDE yields state‑of‑the‑art performance on multi‑view spatial benchmarks, enabling MLLMs to reason robustly across diverse viewpoints.
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.
arXiv Computation and Language
4d ago
Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering
arXiv:2609.38177v1 Announce Type: cross Abstract: Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs...
arXiv AI
Jul 21
OrientSAM: Mitigating Camera-Centric Shortcut in Multimodal Spatial Reasoning via Orientation-Aware Spatial Alignment
arXiv:2607. 17657v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) still struggle with spatial reasoning that requires perspective transformation.
Hugging Face Trending Papers
Sep 3
Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning
The paper introduces FactoSR, a factorized reinforcement learning framework designed to improve spatial reasoning in Vision‑Language Models (VLMs). By decomposing the problem into planar correspondence (XY), depth consistency (Z), and temporal reversibility (T), FactoSR addresses the dimensional mismatch between 2D visual inputs and 3D physical reasoning. Experiments on multi‑view and video benchmarks show significant performance gains, with a 5.9% improvement on VSI‑Bench and 4.5% on All‑Angles‑Bench.
arXiv Computer Vision
Sep 4
Unfold The World: Factorize 4D Properties in Reinforcing Spatial Reasoning
The paper introduces FactoSR, a factorized reinforcement learning framework designed to improve spatial reasoning in Vision‑Language Models by addressing a dimensional mismatch between 2D visual inputs and the 3D+temporal nature of the physical world. FactoSR decomposes the reasoning task into three orthogonal geometric sub‑objectives—planar correspondence (XY), depth consistency (Z), and temporal reversibility (T)—and optimizes these constraints within a unified policy learning mechanism. Experiments on multi‑view and video benchmarks show that this decomposition yields significant performance gains, achieving a 5.9% improvement on VSI‑Bench and 4.5% on All‑Angles‑Bench.