arXiv:2608. 14138v1 Announce Type: cross Abstract: Spatial perception and reasoning from visual observations require recovering geometric structure, establishing correspondences, and understanding spatial relations.
arXiv:2607. 16409v1 Announce Type: cross Abstract: Unified Multimodal Large Language Models (MLLMs) offer a promising paradigm for unifying visual understanding and generation, yet they still struggle to follow complex spatial instructions and logical constraints in controllable image generation.
arXiv:2610.23416v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have significantly advanced instruction-driven perception through the "Embedding-as-Mask" paradigm. However, e...
Object-Uni is a unified model that integrates pose perception, spatial reasoning, pose-conditioned generation, and novel view synthesis for object-centric spatial understanding and controllable image generation. It treats object pose as an explicit geometric variable shared across tasks and introduces a viewpoint-based orientation abstraction to make pose interpretable by multimodal large language models. The authors also create a new benchmark, UniSpatial-80K, and demonstrate that Object‑Uni improves both pose understanding and pose‑controllable generation compared to existing models.
Layout-to-Image generation has made substantial progress in spatial and object-level control. However, existing methods still struggle with complex scenes containing many overlapping and interacting o...
arXiv:2610.09071v1 Announce Type: new Abstract: Layout-to-Image generation has made substantial progress in spatial and object-level control. However, existing methods still struggle with complex sce...
DepthEvidence is a 4B multimodal language model that integrates dense metric depth predictions into language generation. It employs a camera‑conditioned decoder to produce full‑resolution depth maps and a dense‑to‑language interface that converts these predictions into object‑aligned geometry tokens. The model is trained with geometric supervision and instruction tuning, and it sets new state‑of‑the‑art results on a Depth‑VQA benchmark and on instance‑level metric depth estimation across nine datasets.
The paper introduces ReImaGin, a method that uses image generation models as a flexible visual reasoning tool for multimodal large language models. Unlike traditional fixed-function vision tools, ReImaGin accepts natural language commands and can perform open-ended visual operations such as removing occlusions or creating floorplans from multiple views. Experiments on six diverse visual reasoning tasks show that ReImaGin outperforms both text-only reasoning and specialist vision-tool baselines, achieving up to a 25% improvement.
arXiv:2610.20610v1 Announce Type: new Abstract: Generating novel views from limited observations requires preserving both the appearance and spatial structure of a scene. Although recent approaches e...
ScenePilot introduces a retrieval‑augmented Grow‑and‑Repair framework for text‑driven 3D indoor scene generation. It uses a Hierarchical Retrieval‑Augmented Planning module to fetch room, group, and anchor layout priors, then incrementally inserts object groups with a base generator, while a Reinforcement Multimodal Repair module performs lightweight local corrections after each insertion and a final global repair. The approach is trained on a new SceneReverse‑17k dataset of perturbed scenes, enabling the policy to predict structured move‑rotate‑scale actions from rendered views, scene state, retrieved priors, and edit history, thereby improving physical plausibility, functional coherence, and controllability without heavy full‑scene optimization.
arXiv:2610.19108v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) have been widely applied in embodied agents and robotics for vision tasks. However, MLLMs suffer from limita...
Although multimodal large language models (MLLMs) have achieved remarkable progress, understanding 3D spatial relationships from 2D images remains a critical challenge. Existing methods primarily rely on symbolic text tokens, which inherently lack the fidelity to represent continuous geometric information.