Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations

• URL: http://arxiv.org/abs/2609.03657v1
• Date: Thu, 03 Sep 2026 10:54:49 GMT
• Title: Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological Perturbations
• Abstract summary: 3D scene representations like NeRF and 3D Gaussian Splatting suffer severe artifacts in sparse-view settings.<n>We propose 3D Morphological Perturbations as an optimization-free regularizer that preserves spatial consistency.<n>Our approach maintains visual fidelity while reducing mean depth error by 12.5% over state-of-the-art image-to-image 3D artifact refiners.
• Score: 8.600397756762495
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D scene representations like NeRF and 3D Gaussian Splatting (3DGS) suffer severe artifacts in sparse-view settings. Recent generative 3D artifact fixers attempt to address this, but rely on paired corrupted and clean renders requiring costly, per-scene reconstructions across varying view configurations. While 2D image augmentations act as instant regularizers, no explicit equivalents exist for 3D representations to preserve spatial consistency across views, an essential property for 3D-aware training. We propose 3D Morphological Perturbations as an optimization-free regularizer that preserves spatial consistency. Leveraging explicit 3DGS, we treat each Gaussian as a fundamental building block - analogous to a 2D pixel - and apply perturbations across its morphological parameter space via scale, rotation, and pruning. Our method eliminates per-scene 3DGS optimization loops from dataset curation while enabling models to learn stronger geometric priors than sparse-view baselines in diagnostic ablations conducted on a lightweight video diffusion sandbox. Scaled to a 14B-parameter video model via ControlNet, our approach maintains visual fidelity while reducing mean depth error by 12.5% over state-of-the-art image-to-image 3D artifact refiners, ultimately boosting downstream robotics policy success rates by up to 8.0% across 3 of 4 manipulation tasks.

Related papers

• Extend3D: Town-Scale 3D Generation [31.052455723067684]
  We propose Extend3D, a training-free pipeline for 3D scene generation from a single image.<n>By dividing the extended latent space into overlapping patches, we apply the object-centric 3D generative model to each patch and couple them at each time step.<n>Treating the incompleteness of 3D structure as noise during 3D refinement enables 3D completion via a concept, which we term under-noising.
  arXiv  Detail & Related papers  (2026-03-31T07:55:04Z)
• S2D: Sparse to Dense Lifting for 3D Reconstruction with Minimal Inputs [53.597239706600455]
  We introduce Sparse to Dense lifting (S2D), a novel pipeline that bridges the two representations and achieves high-quality 3DGS reconstruction with minimal inputs.<n>Experiments show that S2D achieves the best consistency in generating novel view guidance and first-tier sparse view reconstruction quality under different input sparsity.
  arXiv  Detail & Related papers  (2026-03-11T15:37:20Z)
• EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis [61.1662426227688]
  Existing NeRF and 3DGS-based methods show promising results in achieving photorealistic renderings but require slow, per-scene optimization.<n>We introduce EVolSplat, an efficient 3D Gaussian Splatting model for urban scenes that works in a feed-forward manner.
  arXiv  Detail & Related papers  (2025-03-26T02:47:27Z)
• GaussRender: Learning 3D Occupancy with Gaussian Rendering [86.89653628311565]
  GaussRender is a module that improves 3D occupancy learning by enforcing projective consistency.<n>Our method penalizes 3D configurations that produce inconsistent 2D projections, thereby enforcing a more coherent 3D structure.
  arXiv  Detail & Related papers  (2025-02-07T16:07:51Z)
• Enhancing Single Image to 3D Generation using Gaussian Splatting and Hybrid Diffusion Priors [17.544733016978928]
  3D object generation from a single image involves estimating the full 3D geometry and texture of unseen views from an unposed RGB image captured in the wild. Recent advancements in 3D object generation have introduced techniques that reconstruct an object's 3D shape and texture. We propose bridging the gap between 2D and 3D diffusion models to address this limitation.
  arXiv  Detail & Related papers  (2024-10-12T10:14:11Z)
• ScalingGaussian: Enhancing 3D Content Creation with Generative Gaussian Splatting [30.99112626706754]
  The creation of high-quality 3D assets is paramount for applications in digital heritage, entertainment, and robotics. Traditionally, this process necessitates skilled professionals and specialized software for modeling. We introduce a novel 3D content creation framework, which generates 3D textures efficiently.
  arXiv  Detail & Related papers  (2024-07-26T18:26:01Z)
• GSD: View-Guided Gaussian Splatting Diffusion for 3D Reconstruction [52.04103235260539]
  We present a diffusion model approach based on Gaussian Splatting representation for 3D object reconstruction from a single view. The model learns to generate 3D objects represented by sets of GS ellipsoids. The final reconstructed objects explicitly come with high-quality 3D structure and texture, and can be efficiently rendered in arbitrary views.
  arXiv  Detail & Related papers  (2024-07-05T03:43:08Z)
• PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting [59.277480452459315]
  We propose a principled sensitivity pruning score that preserves visual fidelity and foreground details at significantly higher compression ratios.<n>We also propose a multi-round prune-refine pipeline that can be applied to any pretrained 3D-GS model without changing its training pipeline.
  arXiv  Detail & Related papers  (2024-06-14T17:53:55Z)
• ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections [71.46546520120162]
  Estimating 3D articulated shapes like animal bodies from monocular images is inherently challenging. We propose ARTIC3D, a self-supervised framework to reconstruct per-instance 3D shapes from a sparse image collection in-the-wild. We produce realistic animations by fine-tuning the rendered shape and texture under rigid part transformations.
  arXiv  Detail & Related papers  (2023-06-07T17:47:50Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.