TSGaussian: Semantic and Depth-Guided Target-Specific Gaussian Splatting from Sparse Views

• URL: http://arxiv.org/abs/2412.10051v1
• Date: Fri, 13 Dec 2024 11:26:38 GMT
• Title: TSGaussian: Semantic and Depth-Guided Target-Specific Gaussian Splatting from Sparse Views
• Authors: Liang Zhao, Zehan Bao, Yi Xie, Hong Chen, Yaohui Chen, Weifu Li,
• Abstract summary: TSGaussian is a novel framework that combines semantic constraints with depth priors to avoid geometry degradation in novel view synthesis tasks. Our approach prioritizes computational resources on designated targets while minimizing background allocation. Extensive experiments demonstrate that TSGaussian outperforms state-of-the-art methods on three standard datasets.
• Score: 18.050257821756148
• License:
• Abstract: Recent advances in Gaussian Splatting have significantly advanced the field, achieving both panoptic and interactive segmentation of 3D scenes. However, existing methodologies often overlook the critical need for reconstructing specified targets with complex structures from sparse views. To address this issue, we introduce TSGaussian, a novel framework that combines semantic constraints with depth priors to avoid geometry degradation in challenging novel view synthesis tasks. Our approach prioritizes computational resources on designated targets while minimizing background allocation. Bounding boxes from YOLOv9 serve as prompts for Segment Anything Model to generate 2D mask predictions, ensuring semantic accuracy and cost efficiency. TSGaussian effectively clusters 3D gaussians by introducing a compact identity encoding for each Gaussian ellipsoid and incorporating 3D spatial consistency regularization. Leveraging these modules, we propose a pruning strategy to effectively reduce redundancy in 3D gaussians. Extensive experiments demonstrate that TSGaussian outperforms state-of-the-art methods on three standard datasets and a new challenging dataset we collected, achieving superior results in novel view synthesis of specific objects. Code is available at: https://github.com/leon2000-ai/TSGaussian.

Related papers

• Planar Gaussian Splatting [42.74999794635269]
  Planar Gaussian Splatting (PGS) is a novel neural rendering approach to learn the 3D geometry and parse the 3D planes of a scene. The PGS achieves state-of-the-art performance in 3D planar reconstruction without requiring either 3D plane labels or depth supervision.
  arXiv  Detail & Related papers  (2024-12-02T19:46:43Z)
• CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes [53.107474952492396]
  CityGaussianV2 is a novel approach for large-scale scene reconstruction. We implement a decomposed-gradient-based densification and depth regression technique to eliminate blurry artifacts and accelerate convergence. Our method strikes a promising balance between visual quality, geometric accuracy, as well as storage and training costs.
  arXiv  Detail & Related papers  (2024-11-01T17:59:31Z)
• ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining [104.34751911174196]
  We build a large-scale dataset of 3DGS using ShapeNet and ModelNet datasets. Our dataset ShapeSplat consists of 65K objects from 87 unique categories. We introduce textbftextitGaussian-MAE, which highlights the unique benefits of representation learning from Gaussian parameters.
  arXiv  Detail & Related papers  (2024-08-20T14:49:14Z)
• Implicit Gaussian Splatting with Efficient Multi-Level Tri-Plane Representation [45.582869951581785]
  Implicit Gaussian Splatting (IGS) is an innovative hybrid model that integrates explicit point clouds with implicit feature embeddings. We introduce a level-based progressive training scheme, which incorporates explicit spatial regularization. Our algorithm can deliver high-quality rendering using only a few MBs, effectively balancing storage efficiency and rendering fidelity.
  arXiv  Detail & Related papers  (2024-08-19T14:34:17Z)
• SA-GS: Semantic-Aware Gaussian Splatting for Large Scene Reconstruction with Geometry Constrain [43.80789481557894]
  We propose a novel method, named SA-GS, for fine-grained 3D geometry reconstruction using semantic-aware 3D Gaussian Splats. We leverage prior information stored in large vision models such as SAM and DINO to generate semantic masks. We extract the point cloud using a novel probability density-based extraction method, transforming Gaussian Splats into a point cloud crucial for downstream tasks.
  arXiv  Detail & Related papers  (2024-05-27T08:15:10Z)
• CLIP-GS: CLIP-Informed Gaussian Splatting for Real-time and View-consistent 3D Semantic Understanding [32.76277160013881]
  We present CLIP-GS, which integrates semantics from Contrastive Language-Image Pre-Training (CLIP) into Gaussian Splatting. SAC exploits the inherent unified semantics within objects to learn compact yet effective semantic representations of 3D Gaussians. We also introduce a 3D Coherent Self-training (3DCS) strategy, resorting to the multi-view consistency originated from the 3D model.
  arXiv  Detail & Related papers  (2024-04-22T15:01:32Z)
• SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition [66.56357905500512]
  3D Gaussian Splatting has emerged as an alternative 3D representation for novel view synthesis. We propose SAGD, a conceptually simple yet effective boundary-enhanced segmentation pipeline for 3D-GS. Our approach achieves high-quality 3D segmentation without rough boundary issues, which can be easily applied to other scene editing tasks.
  arXiv  Detail & Related papers  (2024-01-31T14:19:03Z)
• Learning Segmented 3D Gaussians via Efficient Feature Unprojection for Zero-shot Neural Scene Segmentation [16.57158278095853]
  Zero-shot neural scene segmentation serves as an effective way for scene understanding. Existing models, especially the efficient 3D Gaussian-based methods, struggle to produce compact segmentation results. Our work proposes the Feature Unprojection and Fusion module as the segmentation field. We show that our model surpasses baselines on zero-shot semantic segmentation task, improving by 10% mIoU over the best baseline.
  arXiv  Detail & Related papers  (2024-01-11T14:05:01Z)
• FSGS: Real-Time Few-shot View Synthesis using Gaussian Splatting [58.41056963451056]
  We propose a few-shot view synthesis framework based on 3D Gaussian Splatting. This framework enables real-time and photo-realistic view synthesis with as few as three training views. FSGS achieves state-of-the-art performance in both accuracy and rendering efficiency across diverse datasets.
  arXiv  Detail & Related papers  (2023-12-01T09:30:02Z)
• LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS [55.85673901231235]
  We introduce LightGaussian, a method for transforming 3D Gaussians into a more compact format. Inspired by Network Pruning, LightGaussian identifies Gaussians with minimal global significance on scene reconstruction. LightGaussian achieves an average 15x compression rate while boosting FPS from 144 to 237 within the 3D-GS framework.
  arXiv  Detail & Related papers  (2023-11-28T21:39:20Z)
• GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting [51.96353586773191]
  We introduce textbfGS-SLAM that first utilizes 3D Gaussian representation in the Simultaneous Localization and Mapping system. Our method utilizes a real-time differentiable splatting rendering pipeline that offers significant speedup to map optimization and RGB-D rendering. Our method achieves competitive performance compared with existing state-of-the-art real-time methods on the Replica, TUM-RGBD datasets.
  arXiv  Detail & Related papers  (2023-11-20T12:08:23Z)

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.