SSMNBench shows that MLLMs suffer distraction degradation on single-view-sufficient tasks and fail to integrate geometric evidence across views, instead relying on semantic averaging and view preference.
hub
A Survey on 3D Gaussian Splatting
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
abstract
3D Gaussian splatting (GS) has emerged as a transformative technique in radiance fields. Unlike mainstream implicit neural models, 3D GS uses millions of learnable 3D Gaussians for an explicit scene representation. Paired with a differentiable rendering algorithm, this approach achieves real-time rendering and unprecedented editability, making it a potential game-changer for 3D reconstruction and representation. In the present paper, we provide the first systematic overview of the recent developments and critical contributions in 3D GS. We begin with a detailed exploration of the underlying principles and the driving forces behind the emergence of 3D GS, laying the groundwork for understanding its significance. A focal point of our discussion is the practical applicability of 3D GS. By enabling unprecedented rendering speed, 3D GS opens up a plethora of applications, ranging from virtual reality to interactive media and beyond. This is complemented by a comparative analysis of leading 3D GS models, evaluated across various benchmark tasks to highlight their performance and practical utility. The survey concludes by identifying current challenges and suggesting potential avenues for future research. Through this survey, we aim to provide a valuable resource for both newcomers and seasoned researchers, fostering further exploration and advancement in explicit radiance field.
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2representative citing papers
HairGPT reframes 3D hairstyle synthesis as dual-decoupled autoregressive strand sequence modeling with geometric tokenization for semantic control and rare style generation.
GETA-3DGS is the first automatic joint structured pruning and quantization framework for 3D Gaussian Splatting, achieving roughly 5x storage reduction on standard datasets without per-scene thresholds.
BiSplat-WRF applies 2D planar Gaussians rendered on angular domains plus a bilinear spatial transformer to capture electromagnetic interactions, outperforming prior NeRF and GS methods on SSIM for wireless radiance field reconstruction.
DOC-GS uses dual-domain calibration with continuous depth-guided dropout in optimization and dark channel prior evidence in observation to model and prune unreliable Gaussians, reducing haze and distortions in sparse-view 3DGS.
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.
GRay is a ray tracer for 3D Gaussians that exploits dense small primitives for logarithmic scaling, rendering nearly 4x faster and optimizing nearly 10x faster than prior ray tracing while remaining competitive with splatting at somewhat lower quality.
A 3D Gaussian Map enriched by open-set semantic grouping and paired with multi-level action prediction improves vision-language navigation performance on R2R, R4R, and REVERIE benchmarks.
RxGS delivers a single unified 3DGS model for RF synthesis that generalizes across seen and unseen receivers by freezing shared geometry and conditioning directional radiance on receiver position.
PairDropGS uses paired dropout with low-frequency consistency regularization and progressive scheduling to stabilize and improve sparse-view 3D Gaussian Splatting.
A dynamic training framework for 3D Gaussian Splatting alternates incremental pruning and adaptive growing of primitives to maintain high rendering quality at up to 80% lower peak memory than standard 3DGS.
ESCAPE combines spatio-temporal fusion mapping for depth-free 3D memory with a memory-driven grounding module and adaptive execution policy to reach 65.09% success on ALFRED test-seen long-horizon mobile manipulation tasks.
GS4City derives geometry-grounded semantic masks from LoD3 CityGML models via raycasting and fuses them with 2D foundation model outputs to supervise identity encodings on Gaussians, improving coarse and fine semantic segmentation on urban datasets.
PointSplat uses 3D-geometry-only pruning and a dual-branch transformer to reduce Gaussian count in 3DGS scenes, delivering competitive quality and better efficiency without per-scene fine-tuning.
ACE-GS adds momentum consistency densification, statistical sparsification, and residual frequency compensation to 3D Gaussian Splatting, claiming 3.7x faster training, 3-5 minute convergence, and up to 0.89 dB PSNR gain with compact models.
Structure-guided dynamic 3DGS methods deliver superior reconstruction fidelity and compactness on D-NeRF while gaussian-centric methods provide higher rendering speeds at the cost of quality variability and storage.
A survey of 3D representation families that highlights the shift from discrete explicit formats to continuous implicit neural and primitive-based ones.
A survey that categorizes and summarizes methods applying 3D Gaussian Splatting to segmentation, editing, generation, and related tasks, including datasets and evaluation protocols.
The NTIRE 2026 challenge reports measurable progress in 3D reconstruction pipelines that handle real-world low-light and smoke degradation via the RealX3D benchmark.
citing papers explorer
-
SSMNBench: Diagnosing Image-based Cross-View Human-Object Understanding via Single-View Sufficiency and Multi-View Necessity
SSMNBench shows that MLLMs suffer distraction degradation on single-view-sufficient tasks and fail to integrate geometric evidence across views, instead relying on semantic averaging and view preference.
-
HairGPT: Strand-as-Language Autoregressive Modeling for Realistic 3D Hairstyle Synthesis
HairGPT reframes 3D hairstyle synthesis as dual-decoupled autoregressive strand sequence modeling with geometric tokenization for semantic control and rare style generation.
-
GETA-3DGS: Automatic Joint Structured Pruning and Quantization for 3D Gaussian Splatting
GETA-3DGS is the first automatic joint structured pruning and quantization framework for 3D Gaussian Splatting, achieving roughly 5x storage reduction on standard datasets without per-scene thresholds.
-
Planar Gaussian Splatting with Bilinear Spatial Transformer for Wireless Radiance Field Reconstruction
BiSplat-WRF applies 2D planar Gaussians rendered on angular domains plus a bilinear spatial transformer to capture electromagnetic interactions, outperforming prior NeRF and GS methods on SSIM for wireless radiance field reconstruction.
-
DOC-GS: Dual-Domain Observation and Calibration for Reliable Sparse-View Gaussian Splatting
DOC-GS uses dual-domain calibration with continuous depth-guided dropout in optimization and dark channel prior evidence in observation to model and prune unreliable Gaussians, reducing haze and distortions in sparse-view 3DGS.
-
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.
-
GRay: Ray Tracing 3D Gaussians Near the Speed of Splats
GRay is a ray tracer for 3D Gaussians that exploits dense small primitives for logarithmic scaling, rendering nearly 4x faster and optimizing nearly 10x faster than prior ray tracing while remaining competitive with splatting at somewhat lower quality.
-
3D Gaussian Map with Open-Set Semantic Grouping for Vision-Language Navigation
A 3D Gaussian Map enriched by open-set semantic grouping and paired with multi-level action prediction improves vision-language navigation performance on R2R, R4R, and REVERIE benchmarks.
-
RxGS: Receiver-Generalizable 3D Gaussian Splatting for Radio-Frequency Data Synthesis
RxGS delivers a single unified 3DGS model for RF synthesis that generalizes across seen and unseen receivers by freezing shared geometry and conditioning directional radiance on receiver position.
-
PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting
PairDropGS uses paired dropout with low-frequency consistency regularization and progressive scheduling to stabilize and improve sparse-view 3D Gaussian Splatting.
-
Gaussians on a Diet: High-Quality Memory-Bounded 3D Gaussian Splatting Training
A dynamic training framework for 3D Gaussian Splatting alternates incremental pruning and adaptive growing of primitives to maintain high rendering quality at up to 80% lower peak memory than standard 3DGS.
-
ESCAPE: Episodic Spatial Memory and Adaptive Execution Policy for Long-Horizon Mobile Manipulation
ESCAPE combines spatio-temporal fusion mapping for depth-free 3D memory with a memory-driven grounding module and adaptive execution policy to reach 65.09% success on ALFRED test-seen long-horizon mobile manipulation tasks.
-
GS4City: Hierarchical Semantic Gaussian Splatting via City-Model Priors
GS4City derives geometry-grounded semantic masks from LoD3 CityGML models via raycasting and fuses them with 2D foundation model outputs to supervise identity encodings on Gaussians, improving coarse and fine semantic segmentation on urban datasets.
-
PointSplat: Efficient Geometry-Driven Pruning and Transformer Refinement for 3D Gaussian Splatting
PointSplat uses 3D-geometry-only pruning and a dual-branch transformer to reduce Gaussian count in 3DGS scenes, delivering competitive quality and better efficiency without per-scene fine-tuning.
-
ACE-GS: Acing the Trade-off with Accurate, Compact and Efficient 3D Gaussian Splatting
ACE-GS adds momentum consistency densification, statistical sparsification, and residual frequency compensation to 3D Gaussian Splatting, claiming 3.7x faster training, 3-5 minute convergence, and up to 0.89 dB PSNR gain with compact models.
-
Beyond Static Gaussians: An Empirical Investigation of Architectural Paradigms for Dynamic 3D Scene Reconstruction
Structure-guided dynamic 3DGS methods deliver superior reconstruction fidelity and compactness on D-NeRF while gaussian-centric methods provide higher rendering speeds at the cost of quality variability and storage.
-
Recent Advances and Trends in Learning-based 3D Representations
A survey of 3D representation families that highlights the shift from discrete explicit formats to continuous implicit neural and primitive-based ones.
-
A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation
A survey that categorizes and summarizes methods applying 3D Gaussian Splatting to segmentation, editing, generation, and related tasks, including datasets and evaluation protocols.
-
NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results
The NTIRE 2026 challenge reports measurable progress in 3D reconstruction pipelines that handle real-world low-light and smoke degradation via the RealX3D benchmark.