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
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.
Forward citations
Cited by 37 Pith papers
-
Beyond a Single Light: A Large-Scale Aerial Dataset for Urban Scene Reconstruction Under Varying Illumination
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.
-
Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual Grounding
Representing bounding-box coordinates as axis-specific hundreds, tens, and ones tokens, plus a geometry-aware GRPO reward, improves generative visual grounding accuracy.
-
Manifold-GS: Certified Hybrid Assets via Varifold-Conservative Gaussian Splatting
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.
-
GenSplatCodec: Feed-Forward Gaussian Splatting Compression via One-Step Diffusion
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.
-
IoU-PD: IoU-Aware Privileged Distillation for Visual Grounding with Multimodal Large Language Models
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.
-
Nexus: Native Mesh Generation with Diffusion
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.
-
ECO: Incremental Ego-Centric Octree Update for Point Streams
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.
-
Targeted Structure Completion for Sparse-View 3D Reconstruction in Autonomous Driving
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.
-
City-Level 3D Surface Reconstruction with Viewpoint Orientation Partitioning and Scene Completion
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.
-
Signal Structure-Aware Gaussian Splatting for Large-Scale Scene Reconstruction
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.
-
You Only Gaussian Once: Controllable 3D Gaussian Splatting for Ultra-Densely Sampled Scenes
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.
-
Smol-GS: Compact Representations for Abstract 3D Gaussian Splatting
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.
-
ChronoGS: Disentangling Invariants and Changes in Multi-Period Scenes
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.
-
VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
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.
-
Scale-GS: Efficient Scalable Gaussian Splatting via Redundancy-filtering Training on Streaming Content
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.
-
LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos
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...
-
CF3: Compact and Fast 3D Feature Fields
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.
-
No Redundancy, No Stall: Lightweight Streaming 3D Gaussian Splatting for Real-time Rendering
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.
-
SLTarch: Towards Scalable Point-Based Neural Rendering by Taming Workload Imbalance and Memory Irregularity
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.
-
GS-Occ3D: Scaling Vision-only Occupancy Reconstruction with Gaussian Splatting
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...
-
ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting
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.
-
RegGS: Unposed Sparse Views Gaussian Splatting with 3DGS Registration
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.
-
Virtual Memory for 3D Gaussian Splatting
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.
-
On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images
An incremental pipeline jointly estimates camera poses and 3D Gaussian primitives at capture speed, handling large ordered photo sequences with anchors and progressive merging.
-
Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting
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.
-
CityGo: Lightweight Urban Modeling and Rendering with Proxy Buildings and Residual Gaussians
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.
-
HaloGS: Loose Coupling of Compact Geometry and Gaussian Splats for 3D Scenes
A dual representation using learnable triangles plus neural Gaussians achieves competitive rendering and more compact geometric abstractions on common 3D scene benchmarks.
-
Large Images are Gaussians: High-Quality Large Image Representation with Levels of 2D Gaussian Splatting
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.
-
Proxy-GS: Unified Occlusion Priors for Training and Inference in Structured 3D Gaussian Splatting
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...
-
AG$^2$aussian: Anchor-Graph Structured Gaussian Splatting for Instance-Level 3D Scene Understanding and Editing
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...
-
Enhanced Velocity Field Modeling for Gaussian Video Reconstruction
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.
-
Wavelet-GS: 3D Gaussian Splatting with Wavelet Decomposition
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.
-
SD-GS: Structured Deformable 3D Gaussians for Efficient Dynamic Scene Reconstruction
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.
-
LocalDyGS: Multi-view Global Dynamic Scene Modeling via Adaptive Local Implicit Feature Decoupling
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...
-
SuperGS: Consistent and Detailed 3D Super-Resolution Scene Reconstruction via Gaussian Splatting
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.
-
Perceive-Sample-Compress: Towards Real-Time 3D Gaussian Splatting
A three-stage perceive-sample-compress framework for 3D Gaussian Splatting improves rendering fidelity and storage efficiency across small and large scenes.
-
Reconstructing 4D Spatial Intelligence: A Survey
A review that classifies 4D scene reconstruction methods into five progressive levels: low-level cues, scene components, dynamic scenes, interactions, and physics.
Discussion (0). Sign in to comment.