arXiv:2604. 02546v3 Announce Type: replace-cross Abstract: Pretraining 3D encoders through alignment with Contrastive Language-Image Pre-training (CLIP) has emerged as a promising direction for learning generalizable representations for 3D scene understanding.
arXiv:2604. 02546v2 Announce Type: replace-cross Abstract: Pretraining 3D encoders by aligning with Contrastive Language Image Pretraining (CLIP) has emerged as a promising direction to learn generalizable representations for 3D scene understanding.
arXiv:2607. 21595v1 Announce Type: cross Abstract: Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning.
arXiv:2606. 07117v1 Announce Type: cross Abstract: This paper presents Native3D, the first end-to-end 3D scene generation framework that completely bypasses 2D intermediate representations.
Open vocabulary 3D scene understanding is essential for next-generation interactive systems, empowering users to intuitively query and navigate reconstructed environments using natural language. However, current 3D Gaussian frameworks are often bottlenecked by restrictive multiview capture requirements, costly scene-specific optimization, and the massive memory overhead of storing dense language features.
arXiv:2608.21136v1 Announce Type: new Abstract: Recently, open-vocabulary zero-shot 3D scene understanding using vision foundation models has emerged as a promising alternative to data-intensive supe...
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...
GaussianDS introduces a depth‑supervised framework for 3D Gaussian Splatting that jointly optimizes RGB appearance, depth, and compact semantics from scratch. By arranging multi‑view images into a pose‑aware pseudo‑video and propagating view‑consistent masks via SAM2, the method aligns semantic lifting with geometric cues, using depth supervision and edge‑aware refinement to curb semantic drift and boundary leakage. The approach achieves state‑of‑the‑art performance on LERF and 3D‑OVS benchmarks while preserving high‑fidelity reconstruction and enabling downstream tasks such as 3D object removal.
arXiv:2606. 03100v1 Announce Type: cross Abstract: Recently, zero-shot 3D scene understanding via 2D Vision-Language Models (VLMs) has gained increasing research interest due to their promising spatial reasoning capabilities.
arXiv:2606. 05833v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) excel at 2D semantic understanding but lack intrinsic 3D awareness, resulting in representations that fail to maintain geometric and spatial consistency across video frames.
Multimodal Large Language Models (MLLMs) excel at 2D semantic understanding but lack intrinsic 3D awareness, resulting in representations that fail to maintain geometric and spatial consistency across video frames. Given the scarcity of large-scale 3D data, we present GeoVR, a novel framework that learns geometric representations using purely 2D video sequences.
arXiv:2511. 16624v2 Announce Type: replace-cross Abstract: We present SAM 3D, a generative model for visually grounded 3D object reconstruction, predicting geometry, texture, and layout from a single image.
arXiv:2610.02021v1 Announce Type: cross Abstract: Recent vision-language models (VLMs) exhibit remarkable generalization and reasoning abilities, yet 3D understanding in these models is limited by da...