Beyond Existance: Fulfill 3D Reconstructed Scenes with Pseudo Details

• URL: http://arxiv.org/abs/2503.04037v1
• Date: Thu, 06 Mar 2025 02:46:10 GMT
• Title: Beyond Existance: Fulfill 3D Reconstructed Scenes with Pseudo Details
• Authors: Yifei Gao, Jun Huang, Lei Wang, Ruiting Dai, Jun Cheng,
• Abstract summary: We introduce a new training method that integrates diffusion models and multi-scale training using pseudo-ground-truth data.<n>Our method achieves state-of-the-art performance across various benchmarks and extends the capabilities of 3D reconstruction beyond training datasets.
• Score: 12.167127919679022
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The emergence of 3D Gaussian Splatting (3D-GS) has significantly advanced 3D reconstruction by providing high fidelity and fast training speeds across various scenarios. While recent efforts have mainly focused on improving model structures to compress data volume or reduce artifacts during zoom-in and zoom-out operations, they often overlook an underlying issue: training sampling deficiency. In zoomed-in views, Gaussian primitives can appear unregulated and distorted due to their dilation limitations and the insufficient availability of scale-specific training samples. Consequently, incorporating pseudo-details that ensure the completeness and alignment of the scene becomes essential. In this paper, we introduce a new training method that integrates diffusion models and multi-scale training using pseudo-ground-truth data. This approach not only notably mitigates the dilation and zoomed-in artifacts but also enriches reconstructed scenes with precise details out of existing scenarios. Our method achieves state-of-the-art performance across various benchmarks and extends the capabilities of 3D reconstruction beyond training datasets.

Related papers

• StructGS: Adaptive Spherical Harmonics and Rendering Enhancements for Superior 3D Gaussian Splatting [5.759434800012218]
  StructGS is a framework that enhances 3D Gaussian Splatting (3DGS) for improved novel-view synthesis in 3D reconstruction. Our framework significantly reduces computational redundancy, enhances detail capture and supports high-resolution rendering from low-resolution inputs.
  arXiv  Detail & Related papers  (2025-03-09T05:39:44Z)
• T-3DGS: Removing Transient Objects for 3D Scene Reconstruction [83.05271859398779]
  Transient objects in video sequences can significantly degrade the quality of 3D scene reconstructions. We propose T-3DGS, a novel framework that robustly filters out transient distractors during 3D reconstruction using Gaussian Splatting.
  arXiv  Detail & Related papers  (2024-11-29T07:45:24Z)
• Enhancing Generalizability of Representation Learning for Data-Efficient 3D Scene Understanding [50.448520056844885]
  We propose a generative Bayesian network to produce diverse synthetic scenes with real-world patterns. A series of experiments robustly display our method's consistent superiority over existing state-of-the-art pre-training approaches.
  arXiv  Detail & Related papers  (2024-06-17T07:43:53Z)
• 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)
• Bootstrap-GS: Self-Supervised Augmentation for High-Fidelity Gaussian Splatting [9.817215106596146]
  3D-GS faces limitations when generating novel views that significantly deviate from those encountered during training.<n>We introduce a bootstrapping framework to address this problem.<n>Our approach synthesizes pseudo-ground truth from novel views that align with the limited training set.
  arXiv  Detail & Related papers  (2024-04-29T12:57:05Z)
• FILP-3D: Enhancing 3D Few-shot Class-incremental Learning with Pre-trained Vision-Language Models [59.13757801286343]
  Few-shot class-incremental learning aims to mitigate the catastrophic forgetting issue when a model is incrementally trained on limited data.<n>We introduce the FILP-3D framework with two novel components: the Redundant Feature Eliminator (RFE) for feature space misalignment and the Spatial Noise Compensator (SNC) for significant noise.
  arXiv  Detail & Related papers  (2023-12-28T14:52:07Z)
• Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering [71.44349029439944]
  Recent 3D Gaussian Splatting method has achieved the state-of-the-art rendering quality and speed. We introduce Scaffold-GS, which uses anchor points to distribute local 3D Gaussians. We show that our method effectively reduces redundant Gaussians while delivering high-quality rendering.
  arXiv  Detail & Related papers  (2023-11-30T17:58:57Z)
• Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering [93.94371335579321]
  We propose a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations. Comprehensive experiments underscore our framework's superior generalization capabilities. Our innovative loss functions empower the model to autonomously recover domain-specific scale-and-shift coefficients.
  arXiv  Detail & Related papers  (2023-09-18T12:36:39Z)
• Unbiased 4D: Monocular 4D Reconstruction with a Neural Deformation Model [76.64071133839862]
  Capturing general deforming scenes from monocular RGB video is crucial for many computer graphics and vision applications. Our method, Ub4D, handles large deformations, performs shape completion in occluded regions, and can operate on monocular RGB videos directly by using differentiable volume rendering. Results on our new dataset, which will be made publicly available, demonstrate a clear improvement over the state of the art in terms of surface reconstruction accuracy and robustness to large deformations.
  arXiv  Detail & Related papers  (2022-06-16T17:59:54Z)
• Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training [45.90045513731704]
  This paper revisits an innovative yet simple fully-supervised 3D network pre-training framework. With a redesigned 3D network architecture, reformulated natural images are used to address the problem of data scarcity. Comprehensive experiments on four benchmark datasets demonstrate that the proposed pre-trained models can effectively accelerate convergence.
  arXiv  Detail & Related papers  (2022-01-05T03:11:21Z)
• Learning monocular 3D reconstruction of articulated categories from motion [39.811816510186475]
  Video self-supervision forces the consistency of consecutive 3D reconstructions by a motion-based cycle loss. We introduce an interpretable model of 3D template deformations that controls a 3D surface through the displacement of a small number of local, learnable handles. We obtain state-of-the-art reconstructions with diverse shapes, viewpoints and textures for multiple articulated object categories.
  arXiv  Detail & Related papers  (2021-03-30T13:50:27Z)

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.