Pith. sign in

REVIEW 37 cited by

Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2403.17898 v2 pith:H6PLJ4C4 submitted 2024-03-26 cs.CV

classification cs.CV
keywords renderingdetailsgaussianconsistentd-gslevellevel-of-detaillod-structured
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The recent 3D Gaussian splatting (3D-GS) has shown remarkable rendering fidelity and efficiency compared to NeRF-based neural scene representations. While demonstrating the potential for real-time rendering, 3D-GS encounters rendering bottlenecks in large scenes with complex details due to an excessive number of Gaussian primitives located within the viewing frustum. This limitation is particularly noticeable in zoom-out views and can lead to inconsistent rendering speeds in scenes with varying details. Moreover, it often struggles to capture the corresponding level of details at different scales with its heuristic density control operation. Inspired by the Level-of-Detail (LOD) techniques, we introduce Octree-GS, featuring an LOD-structured 3D Gaussian approach supporting level-of-detail decomposition for scene representation that contributes to the final rendering results. Our model dynamically selects the appropriate level from the set of multi-resolution anchor points, ensuring consistent rendering performance with adaptive LOD adjustments while maintaining high-fidelity rendering results.

Discussion (0). Sign in to comment.

Forward citations

Cited by 37 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Beyond a Single Light: A Large-Scale Aerial Dataset for Urban Scene Reconstruction Under Varying Illumination

    cs.CV 2025-12 conditional novelty 7.0 of 10

    SkyLume contributes 10 real-world UAV urban regions captured at morning, noon, and afternoon with LiDAR-based ground truth, plus the Temporal Consistency Coefficient metric for cross-time albedo stability.

  2. Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding

    cs.CV 2026-08 conditional novelty 6.0 of 10

    Representing bounding-box coordinates as axis-specific hundreds, tens, and ones tokens, plus a geometry-aware GRPO reward, improves generative visual grounding accuracy.

  3. Manifold-GS: Certified Hybrid Assets via Varifold-Conservative Gaussian Splatting

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Gaussian splat scenes can be exported as certified open patches with conservative mass transport, cutting collision-hallucination area versus watertight mesh baselines on three DTU scenes at lower coverage.

  4. GenSplatCodec: Feed-Forward Gaussian Splatting Compression via One-Step Diffusion

    cs.CV 2026-07 conditional novelty 6.0 of 10

    A dual-stream feed-forward 3DGS codec plus geometry-guided one-step diffusion decoding beats cascaded compressors on rate-distortion while keeping multi-view consistency.

  5. IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Training a coordinate-generating VLM with an IoU-aware distillation loss from a teacher that sees the ground-truth box marked on the image improves referring-expression grounding by ~3-4 accuracy points.

  6. Nexus: Native Mesh Generation with Diffusion

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Nexus replaces autoregressive mesh serialization with two coupled diffusion models — octree vertex generation and a latent topology generator — claiming stronger geometry and perceptual quality on Objaverse and Toys4K.

  7. ECO: Incremental Ego-Centric Octree Update for Point Streams

    cs.RO 2026-07 accept novelty 6.0 of 10

    Ego-Centric Octree (ECO) maintains a robot-centered, fixed-volume octree via shift-out/shift-in/overlap incremental updates, reducing update time ~25% vs full rebuild and ~55% vs bounded i-Octree on KITTI.

  8. Targeted Structure Completion for Sparse-View 3D Reconstruction in Autonomous Driving

    cs.CV 2026-07 conditional novelty 6.0 of 10

    FocusGS localizes a 3D geometric ambiguity manifold from depth discontinuities and instantiates continuous Gaussian queries only there, yielding SOTA sparse-view driving reconstruction with far fewer Gaussians.

  9. City-Level 3D Surface Reconstruction with Viewpoint Orientation Partitioning and Scene Completion

    cs.CV 2026-07 conditional novelty 6.0 of 10

    Viewpoint-orientation partitioning of cameras plus selective completion of sparse SfM points enables higher-quality large-scale surface meshes from 3DGS than spatial-block baselines.

  10. Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction

    cs.CV 2026-07 unverdicted novelty 6.0 of 10

    SIG synchronizes training-image resolution and Gaussian densification to measured scene bandwidth, plus sphere constraints on primitives, delivering better PSNR and 1.4–1.5× per-block speedups on large outdoor scenes.

  11. You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    YOGO reformulates stochastic 3D Gaussian Splatting into a deterministic budget-aware system and supplies an ultra-dense dataset to enforce physical fidelity over viewpoint interpolation.

  12. Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting

    cs.CV 2025-11 conditional novelty 6.0 of 10

    A 3D Gaussian Splatting compression method that stores coordinates in an occupancy octree and represents appearance with 8-d learned features, reaching ~4.7-6.4 MB per scene at near-SOTA quality.

  13. ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes

    cs.GR 2025-11 conditional novelty 6.0 of 10

    A single shared Gaussian scaffold with per-period features and opacity gating reconstructs multi-period scenes better than static and dynamic baselines on a new 12-scene benchmark.

  14. VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

    cs.CV 2025-09 conditional novelty 6.0 of 10

    VolSplat predicts 3D Gaussians from a shared voxel grid instead of from image pixels, reporting large gains in sparse-view novel view synthesis on RealEstate10K, ScanNet, and ACID.

  15. Scale-GS: Efficient Scalable Gaussian Splatting via Redundancy-filtering Training on Streaming Content

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A multi-scale Gaussian splatting method that selectively activates fine Gaussians, prunes static regions, and picks informative viewpoints to train streaming video faster and with higher PSNR.

  16. LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

    cs.CV 2025-08 conditional novelty 6.0 of 10

    An incremental 3D Gaussian Splatting pipeline that jointly optimizes camera poses and scene geometry using MASt3R priors and density-adaptive octree anchors achieves state-of-the-art novel view synthesis on casual lon...

  17. CF3: Compact and Fast 3D Feature Fields

    cs.CV 2025-08 conditional novelty 6.0 of 10

    CF3 builds a compact 3D feature field from a pre-trained 3DGS by feature lifting, per-Gaussian autoencoding, and adaptive sparsification, matching baseline segmentation quality with roughly 5% of the Gaussians.

  18. No Redundancy, No Stall: Lightweight Streaming 3D Gaussian Splatting for Real-time Rendering

    cs.AR 2025-07 conditional novelty 6.0 of 10

    A training-free 3DGS acceleration framework using tile warping, depth-based early-stop prediction, and load-balanced streaming hardware that reports 5.41x to 17.3x speedups.

  19. SLTarch: Towards Scalable Point-Based Neural Rendering by Taming Workload Imbalance and Memory Irregularity

    cs.AR 2025-07 conditional novelty 6.0 of 10

    SLTarch uses a subtree-based LoD tree, a dedicated traversal core, and a 2x2 pixel-group splatting scheme to accelerate point-based neural rendering on mobile hardware.

  20. GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting

    cs.CV 2025-07 conditional novelty 6.0 of 10

    A camera-only Gaussian-surfel pipeline reconstructs full Waymo scenes, converts them to binary occupancy labels, and trains CVT-Occ to generalize on Occ3D-Waymo and Occ3D-nuScenes at a level close to or above LiDAR-la...

  21. ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting

    cs.GR 2025-07 conditional novelty 6.0 of 10

    ObjectGS unifies 3D Gaussian scene reconstruction with object-level segmentation by binding each object to local anchors with fixed one-hot ID encodings, improving open-vocabulary and panoptic segmentation.

  22. RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration

    cs.CV 2025-07 conditional novelty 6.0 of 10

    RegGS aligns locally generated 3D Gaussian maps using a Sinkhorn-approximated mixture Wasserstein distance, improving pose estimation and novel view synthesis from sparse unposed views.

  23. Virtual Memory for 3D Gaussian Splatting

    cs.GR 2025-06 conditional novelty 6.0 of 10

    A proxy-mesh visibility buffer with page streaming and level of detail lets 3D Gaussian Splatting render scenes larger than GPU memory while culling occluded Gaussians.

  24. On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images

    cs.CV 2025-06 conditional novelty 6.0 of 10

    An incremental pipeline jointly estimates camera poses and 3D Gaussian primitives at capture speed, handling large ordered photo sequences with anchors and progressive merging.

  25. Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting

    cs.CV 2025-05 conditional novelty 6.0 of 10

    MixGS trains a holistic 3D Gaussian Splatting model with a view-aware decoder and a mixing operation, reporting state-of-the-art rendering quality on four large-scale scenes.

  26. CityGo: Lightweight Urban Modeling and Rendering with Proxy Buildings and Residual Gaussians

    cs.GR 2025-05 conditional novelty 6.0 of 10

    A hybrid of proxy building meshes and residual plus surrounding 3D Gaussians renders large urban scenes in real time on mobile GPUs with substantially less memory than pure 3DGS.

  27. HaloGS: Loose Coupling of Compact Geometry and Gaussian Splats for 3D Scenes

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A dual representation using learnable triangles plus neural Gaussians achieves competitive rendering and more compact geometric abstractions on common 3D scene benchmarks.

  28. Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting

    cs.CV 2025-02 conditional novelty 6.0 of 10

    A two-level 2D Gaussian splatting method with direct covariance optimization fits large images with more Gaussian points and higher PSNR than prior Gaussian-based image representation.

  29. Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting

    cs.CV 2025-09 conditional novelty 5.0 of 10

    A proxy mesh rendered through hardware rasterization provides a cheap occlusion depth prior that culls hidden anchors at inference and guides densification at training, giving Octree-GS-like MLP splatting a 3 to 4x sp...

  30. AG$^2$aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing

    cs.CV 2025-08 conditional novelty 5.0 of 10

    An anchor-graph structured 3D Gaussians representation, with graph-based feature propagation and region growing, achieves cleaner instance-level object selection and better editing/simulation results than free-Gaussia...

  31. Enhanced Velocity Field Modeling for Gaussian Video Reconstruction

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Velocity field rendering with flow-based losses and flow-assisted densification lifts dynamic Gaussian novel-view PSNR by about 2.5 dB on Nvidia-long and Neu3D.

  32. Wavelet-GS: 3D Gaussian Splatting with Wavelet Decomposition

    cs.GR 2025-07 reject novelty 5.0 of 10

    Wavelet-GS splits a 3D point cloud into low- and high-frequency wavelet parts, trains each with its own strategy, plus a relight module, reporting gains over prior 3DGS variants on four datasets.

  33. SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction

    cs.GR 2025-07 conditional novelty 5.0 of 10

    SD-GS combines anchor-based 3D Gaussians with a deformation field and a deformation-aware densification strategy to reconstruct dynamic scenes more compactly and faster than prior 4D Gaussian methods.

  34. LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling

    cs.CV 2025-07 conditional novelty 5.0 of 10

    LocalDyGS reconstructs dynamic scenes by decomposing space into seed-based local regions and generating time-varying Temporal Gaussians, though its claim of being first for large-scale scenes omits the existing Swift4...

  35. SuperGS: Consistent and Detailed 3D Super-Resolution Scene Reconstruction via Gaussian Splatting

    cs.CV 2025-05 conditional novelty 5.0 of 10

    SuperGS outperforms prior Gaussian-splatting methods on high-resolution novel view synthesis by combining a latent feature field, multi-view voting densification, and variational uncertainty weighting.

  36. Perceive-Sample-Compress: Towards Real-Time 3D Gaussian Splatting

    cs.GR 2025-08 conditional novelty 4.0 of 10

    A three-stage perceive-sample-compress framework for 3D Gaussian Splatting improves rendering fidelity and storage efficiency across small and large scenes.

  37. Reconstructing 4D Spatial Intelligence: A Survey

    cs.CV 2025-07 accept novelty 4.0 of 10

    A review that classifies 4D scene reconstruction methods into five progressive levels: low-level cues, scene components, dynamic scenes, interactions, and physics.

Pith tools