arXiv:2610.23050v1 Announce Type: new Abstract: Recent progress in 3D generation has motivated growing interest in compact generative representations of complex 3D scenes. For native 3D Gaussian scen...
OceanXL is a new framework that applies 3D Gaussian Splatting to large-scale underwater scenes by partitioning them into spatially coherent blocks and using adaptive pruning to remove redundant primitives. This divide‑and‑conquer approach improves training efficiency and rendering performance while maintaining global geometric consistency. The authors also release a large underwater dataset and demonstrate that OceanXL achieves favorable scalability, compactness, and efficiency compared to existing baselines, with competitive quality on smaller datasets and smaller model sizes than other underwater methods.
The paper introduces an extension to the OceanSim underwater perception simulator, adding a Synthetic Data Generation pipeline that produces large, automatically labeled, photorealistic datasets with configurable scene and sensor settings. The authors evaluate this pipeline on a real-world sea urchin detection task, examining how different synthetic scene variations influence sim-to-real performance. They discuss the pipeline’s findings, limitations, and future directions for improving rendering fidelity, scene diversity, and sim-to-real generalization.
arXiv:2608.23140v1 Announce Type: new Abstract: Achieving 360{\deg} coverage is critical for the visual perception systems of autonomous vehicles. Fisheye cameras offer a cost-effective solution by e...
SpatialCrafter introduces a two‑stage framework for single‑image world modeling that first generates a global 3D proxy using a Point‑anchored Sparse Structure Flow module, then refines appearance with a Generative Deferred Refiner built on a video diffusion model. The method incorporates Parallel Geometry Injection and Proxy‑Aware Corruption training to integrate the proxy without disrupting the pretrained generative manifold, and it is evaluated on a newly constructed dataset of 115K scenes. Experiments demonstrate that SpatialCrafter outperforms existing approaches, reducing long‑term drift and maintaining consistency under rapid camera motion and extreme viewpoints.
FlowMoDE introduces a coarse‑to‑fine flow‑matching framework for monocular depth estimation that balances efficiency and detail reconstruction. The method first decodes coarse depth conditioned on diffused features from a pre‑trained semantic encoder, then refines fine structural patterns with expanded decoding layers. Trained only on a synthetic indoor dataset, FlowMoDE achieves a 14.1% lower relative error and a 9.9% lower Chamfer distance compared to state‑of‑the‑art methods across five real‑world indoor and outdoor datasets, and demonstrates strong generalization to realistic robotic scenes.
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.
arXiv:2605.12957v2 Announce Type: replace Abstract: Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of do...
ControlFlow3D is a framework that upsamples point clouds by distilling knowledge from pretrained foundation models into a lightweight generation network. It performs conditional flow matching in a latent space defined by a frozen 3D encoder, using unsupervised soft KMeans to cluster multi‑view image tokens and 3D latent tokens into shared prototypes that guide the flow trajectory. A Mamba‑based geometry decoder then maps latent features to dense coordinates with linear complexity, and the authors introduce ShapeNetPU, a 35K‑object multi‑modal benchmark 31 times larger than previous datasets.
VolFill is a generative framework that reconstructs the complete 3D geometry of a scene from a single RGB image, addressing the challenge of inferring hidden structures. It uses a hybrid 3D VAE to encode sparse truncated unsigned distance function grids into a latent space, and a latent Diffusion Transformer to denoise and recover the full scene. By conditioning on a geometry foundation model, VolFill leverages spatial priors and provides a structured representation that enables direct surface extraction and scalable occupancy queries, outperforming existing amodal baselines on SCRREAM and NRGB-D datasets.
Estimating 3D geometry in underwater environments presents unique challenges due to light attenuation, scattering, and the absence of large-scale, high-quality 3D annotations. Pioneering methods rely on massive dense annotations that are impractical in underwater settings.
arXiv:2610.08790v1 Announce Type: new Abstract: Single-image scene generation aims to produce a complete 3D scene mesh from a single image, including surfaces the camera did not observe. While pretra...