Gaussian-JEPA: Joint-Embedding Predictive Learning for 3D Gaussian Splats

• URL: http://arxiv.org/abs/2608.15651v1
• Date: Sun, 16 Aug 2026 09:43:50 GMT
• Title: Gaussian-JEPA: Joint-Embedding Predictive Learning for 3D Gaussian Splats
• Abstract summary: 3D Gaussian Splatting (3DGS) represents 3D content with anisotropic primitives that jointly encode geometry and appearance.<n>We introduce Gaussian-JEPA, which predicts representations of held-out Gaussian token blocks from visible context.
• Score: 91.55220894541151
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 3D Gaussian Splatting (3DGS) represents 3D content with anisotropic primitives that jointly encode geometry and appearance. Fixed-budget encoders consume sampled observations of Gaussian assets, so the same object may be observed through different primitive realizations. Existing self-supervised methods mainly reconstruct masked Gaussian attributes, tying supervision to one sampled realization and requiring an input-space decoder. Latent prediction offers an alternative, but its application to Gaussian tokens requires targets that accommodate coupled attributes and heterogeneous spatial support. We introduce Gaussian-JEPA, which predicts representations of held-out Gaussian token blocks from visible context. An online encoder processes the context, while a shared exponential-moving-average encoder supplies stop-gradient features for multi-scale targets. Complementary target projections and feature-space grounding provide latent supervision without reconstructing Gaussian attributes. We evaluate the features under Gaussian resampling, partial observations, and renderable shape completion, together with transfer to part segmentation and object classification. Compared with matched reconstruction pretraining, Gaussian-JEPA is more consistent across resampled inputs, retains more instance information under partial observations, and provides stronger frozen features for Gaussian completion. These results support latent prediction as an effective objective for reusable 3D Gaussian representations. Code is on the project page (https://amazingren.github.io/Gaussian-JEPA/).

Related papers

• GS^2: Graph-based Spatial Distribution Optimization for Compact 3D Gaussian Splatting [50.2045409672451]
  3D Gaussian Splatting (3DGS) has demonstrated breakthrough performance in novel view synthesis and real-time rendering.<n>It is constrained by the high memory cost due to a huge number of Gaussian points.<n>We propose graph-based spatial distribution optimization for compact 3DGS.
  arXiv  Detail & Related papers  (2026-04-02T10:41:51Z)
• EntropyGS: An Efficient Entropy Coding on 3D Gaussian Splatting [10.987074189295367]
  3DGS demonstrates fast training/rendering with superior visual quality.<n>We begin with a correlation and statistical analysis of 3DGS Gaussian attributes.<n>A factorized and parameterized entropy coding method, EntropyGS, is proposed.
  arXiv  Detail & Related papers  (2025-08-13T22:48:49Z)
• ProtoGS: Efficient and High-Quality Rendering with 3D Gaussian Prototypes [81.48624894781257]
  3D Gaussian Splatting (3DGS) has made significant strides in novel view synthesis but is limited by the substantial number of Gaussian primitives required.<n>Recent methods address this issue by compressing the storage size of densified Gaussians, yet fail to preserve rendering quality and efficiency.<n>We propose ProtoGS to learn Gaussian prototypes to represent Gaussian primitives, significantly reducing the total Gaussian amount without sacrificing visual quality.
  arXiv  Detail & Related papers  (2025-03-21T18:55:14Z)
• GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding [44.68350305790145]
  GaussTR is a novel Transformer framework that unifies sparse 3D modeling with foundation model alignment through Gaussian representations to advance 3D spatial understanding.<n>Experiments on the Occ3D-nuScenes dataset demonstrate GaussTR's state-of-the-art zero-shot performance of 12.27 mIoU, along with a 40% reduction in training time.<n>These results highlight the efficacy of GaussTR for scalable and holistic 3D spatial understanding, with promising implications in autonomous driving and embodied agents.
  arXiv  Detail & Related papers  (2024-12-17T18:59:46Z)
• PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views [116.10577967146762]
  PixelGaussian is an efficient framework for learning generalizable 3D Gaussian reconstruction from arbitrary views. Our method achieves state-of-the-art performance with good generalization to various numbers of views.
  arXiv  Detail & Related papers  (2024-10-24T17:59:58Z)
• ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining [112.40071212468843]
  3D Gaussian Splatting (3DGS) has become the de facto method of 3D representation in many vision tasks.<n>We build a large-scale dataset of 3DGS using the commonly used ShapeNet, ModelNet and averse.<n>We introduce Gaussian-MAE, which highlights the unique benefits of representation learning from Gaussian parameters.
  arXiv  Detail & Related papers  (2024-08-20T14:49:14Z)
• GaussianFormer: Scene as Gaussians for Vision-Based 3D Semantic Occupancy Prediction [70.65250036489128]
  3D semantic occupancy prediction aims to obtain 3D fine-grained geometry and semantics of the surrounding scene. We propose an object-centric representation to describe 3D scenes with sparse 3D semantic Gaussians. GaussianFormer achieves comparable performance with state-of-the-art methods with only 17.8% - 24.8% of their memory consumption.
  arXiv  Detail & Related papers  (2024-05-27T17:59:51Z)

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.