LucidLyra is a framework that reconstructs 3D scenes from video latents in a feed‑forward manner while simultaneously providing open‑vocabulary semantics and instance cues. By distilling knowledge from a camera‑controlled video diffusion model and frozen 2D vision foundation models, it jointly infers 3D Gaussians that encode geometry, appearance, and semantic information without requiring per‑scene optimization or manual 3D annotations. The resulting scenes support novel‑view rendering, open‑vocabulary segmentation, and object grouping, and can be extended to monocular video for dynamic 3D reconstruction.
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:2607. 00832v1 Announce Type: cross Abstract: A single panorama captures the full visual sphere from one camera center, yet confines users to looking around in place without enabling true scene exploration.
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.
WorldSculpt presents a method for generating compositional 3D representations of cluttered scenes with hundreds of objects by adapting a single-object 3D generative prior to multi-view observations. The approach, built on Pixal3D with a multi-view conditioning pathway, can generalize to highly occluded scenes without scene-level training. The authors also introduce the UE-MeshyScene benchmark and demonstrate that their method outperforms prior approaches across various evaluation settings, including converting existing 3DGS worlds into compositional mesh scenes.
Dynamic-Robust Photometric-Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding introduces SPAR, a joint semantic‑geometric encoding architecture that isolates transient dynamic noise before latent space aggregation. The method couples motion estimation with multi‑view visual and semantic learning in a dynamic‑region‑aware end‑to‑end training paradigm, enabling the network to resolve motion conflicts and produce temporally stable scene representations. Experiments on the D‑RE10K benchmark show state‑of‑the‑art performance, achieving high PSNR values for novel view synthesis and an 88.5% mIoU for motion mask prediction in a self‑supervised setting.
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:2604.14025v2 Announce Type: replace-cross Abstract: Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understa...
arXiv:2609.23796v2 Announce Type: replace Abstract: Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open ch...
Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spatial foundation models have enabled generalizable feed-forward 3D reconstruction, most streaming methods remain geometry-centric and lack temporally consistent object-level understanding.
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...
The paper introduces a biologically inspired framework that learns object‑centric visual representations from raw videos without human annotations or camera calibration. By using motion boundaries detected via optical flow and clustering to create pseudo‑instance masks, the method supervises a single‑image encoder with pixel‑level pairwise metric learning. Training on 195 million pseudo‑labeled frames and expanding to 421 million frames through Motion‑Verified Self‑Training, the approach yields Swin‑based encoders that outperform or match supervised and self‑supervised baselines on tasks such as monocular depth estimation, 3D object detection, 3D occupancy prediction, and end‑to‑end planning.
arXiv:2609.23796v1 Announce Type: new Abstract: Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open challe...