arXiv:2607. 06565v1 Announce Type: cross Abstract: Unified 3D foundation models aspire to generate 3D assets and reason about them in language within a single backbone, but their text-3D interaction remains largely implicit.
arXiv:2608. 01185v1 Announce Type: cross Abstract: Recent 3D vision-language models (3D VLMs) construct geometry aware tokens by projecting 2D visual features into world coordinates, enabling spatial reasoning for tasks such as 3D question answering.
arXiv:2605.29655v4 Announce Type: replace Abstract: Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D t...
KaiNinja extends the native 3D generator TRELLIS.2 to produce part-level meshes by introducing a dual‑volume representation that overcomes the single‑sheet limitation of the O‑Voxel grid. It maintains TRELLIS.2’s speed and quality while eliminating the need for external segmentation, and is trained on diverse data including CAD models and assets created by an LLM‑driven agent. The method improves whole‑object fidelity and outperforms other part‑generation pipelines, reducing Chamfer distance by 40% and increasing strict part F‑score by 16%.
arXiv:2608. 15710v1 Announce Type: cross Abstract: We address a fundamental gap in 3D-LLMs: existing models focus on single-object/scene description, struggling with detailed, inter-object comparison.
arXiv:2609.15659v1 Announce Type: cross Abstract: Native 3D generators turn one image into a single mesh. TRELLIS.2 and its peers deliver high-fidelity non-watertight geometry with materials, but the...
arXiv:2605. 20448v2 Announce Type: replace-cross Abstract: Vision-language models reliably name objects in a scene, but do they represent the 3D layout those objects inhabit?
GoDeep is an annotation‑free method for open‑vocabulary 3D scene understanding that uses a vision‑language model solely as a translator to generate structured, entity‑level descriptions of each image. These descriptions are projected and aggregated in a language‑only embedding space, eliminating the need for a 3D training corpus or domain‑specific encoder. The approach achieves competitive performance on ScanNet++ and a cultural heritage benchmark, accurately localizes out‑of‑vocabulary objects, and offers explainable, point‑level predictions.
FAVE (Foveated Adaptive Visual Encoding) is a lightweight, variable‑resolution Vision Transformer that encodes user‑selected image regions at high acuity while maintaining the image’s native geometry. In controlled experiments on small‑object ImageNet crops, FAVE outperforms a fixed‑resolution ViT by 9.4 top‑1 points while using 12.7× fewer FLOPs. When added as a local branch to FastVLM, FAVE improves TextVQA by 1.60 points and GQA attribute accuracy by 1.31 points, achieving a 3.3× speedup over SmolVLM2-2.2B with only 16 extra local tokens.
arXiv:2609.31595v1 Announce Type: new Abstract: 3D scene graphs provide a structured representation of complex environments by encoding objects, their semantic attributes, and the spatial and functio...
The paper investigates how different 2D image backbones affect indoor semantic occupancy prediction in RGB‑D pipelines. By keeping the projection, depth branch, and occupancy head constant and swapping only the image encoder, the authors find that stronger backbones such as DINOv2 and BLIP2 significantly raise mIoU scores compared to the default ResNet‑50. These results show that the choice of image backbone is a major determinant of 3D occupancy accuracy, outweighing many specialized 3D modules.
arXiv:2607. 25912v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong potential for general robot manipulation, but most existing models rely on 2D visual-language backbones and lack fine-grained 3D understanding of target objects, especially under occlusion, pose variation, scale changes, and precise spatial interaction.