ConFixGS repairs feedforward 3D Gaussian Splatting with confidence-aware diffusion priors, delivering up to 3.68 dB PSNR gains and halved FID scores on Waymo, nuScenes, and KITTI novel view synthesis tasks.
hub
Nerf++: Analyzing and improving neural radiance fields
23 Pith papers cite this work. Polarity classification is still indexing.
23
Pith papers citing it
hub tools
citation-role summary
background 3
citation-polarity summary
roles
background 3polarities
background 3representative citing papers
LRM is a large transformer that predicts a NeRF directly from a single image after training on a million-object multi-view dataset.
NeuS introduces a bias-free volume rendering method for signed distance function representations to reconstruct accurate surfaces from 2D images.
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.
Nested SDF mesh shells rasterized by an off-the-shelf non-differentiable rasterizer and alpha-composited enable mesh-based novel-view synthesis on unbounded real-world scenes.
A semi-balanced optimal transport framework with column-capacity constraints for consistent multi-view stylization of 3D Gaussian Splatting.
Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
UnsOcc proposes RenderFusion and GSRefinement to improve 3D semantic occupancy prediction in unstructured scenes by enhancing cross-modal fusion and long-tail supervision, outperforming SOTA on a new mine dataset and nuScenes.
Hybrid Gaussian-voxel scaffolding with surface tethering loss for accurate and efficient monocular 3D surface reconstruction.
RT-Splatting adds a disentangled occupancy-opacity factorization and specular-aware gradient gating to 3D Gaussian Splatting, enabling joint high-fidelity reflection and transmission in real-time novel view synthesis.
RetrieveVGGT enables constant-memory long-context streaming 3D reconstruction by retrieving relevant frames via query-key similarities in VGGT's first attention layer, outperforming StreamVGGT and others.
A framework that structurally enforces divergence-free velocity and long-range transport coherence in 3D fluid reconstruction from 2D videos via divergence-free kernels advecting Lagrangian Gaussian splats.
EnerGS introduces an energy-based soft guidance mechanism for partial geometry in 3D Gaussian Splatting to improve reconstruction quality and reduce overfitting in sparse outdoor settings.
MERID-GS decouples illumination and reflectance at multiple scales with learnable gain and frequency gating to support few-shot low-light 3D Gaussian Splatting and cross-scene generalization.
A CUDA-parallel voxelizer and hierarchical SGGX clustering representation enable faster, more accurate level-of-detail rendering of sparse microgeometry volumes.
BulletGen enhances 4D dynamic scene reconstruction from monocular videos by supervising Gaussian optimization with diffusion-generated frames aligned at a bullet-time step, achieving SOTA on novel-view synthesis and tracking.
PREF introduces a phasor volume and tailored Fourier mapping to let shallow MLPs capture high-frequency signals compactly in 2D images, 3D SDFs, and 5D NeRFs.
TWINGS aligns monocular depth backprojections to triangulated 3D control points via thin-plate splines, densifying the initial point cloud and improving sparse-view 3D Gaussian Splatting (e.g., +2.3 dB PSNR over CoR-GS on DTU 3-view).
ReorgGS reorganizes the Gaussian distribution in converged 3DGS models by resampling centers and covariances to reduce parameterization degeneration and enable better subsequent optimization.
Geometry-guided adaptive placement of bases and virtual viewpoints improves rendering quality and memory use over uniform arrangements in scalable NeRF for large indoor scenes.
CLEAR-NeRF augments standard NeRF with four targeted components for superior photorealism and metric accuracy in multi-ROI unbounded scenes compared to baseline NeRF and SfM-MVS methods.
A literature survey of NeRF and neural field methods from 2020-2025, organized by architecture and application taxonomies with benchmarks and dataset overviews, covering both pre- and post-Gaussian Splatting periods.
citing papers explorer
-
ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes
ConFixGS repairs feedforward 3D Gaussian Splatting with confidence-aware diffusion priors, delivering up to 3.68 dB PSNR gains and halved FID scores on Waymo, nuScenes, and KITTI novel view synthesis tasks.
-
LRM: Large Reconstruction Model for Single Image to 3D
LRM is a large transformer that predicts a NeRF directly from a single image after training on a million-object multi-view dataset.
-
NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction
NeuS introduces a bias-free volume rendering method for signed distance function representations to reconstruct accurate surfaces from 2D images.
-
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.
-
Meshtryoshka: Differentiable Rendering of Real-World Scenes via Mesh Rasterization
Nested SDF mesh shells rasterized by an off-the-shelf non-differentiable rasterizer and alpha-composited enable mesh-based novel-view synthesis on unbounded real-world scenes.
-
Capacity-Controlled Multi-View Stylization of 3D Gaussian Splatting
A semi-balanced optimal transport framework with column-capacity constraints for consistent multi-view stylization of 3D Gaussian Splatting.
-
Lighting-Consistent Object Transfer Across Radiance Fields
Diffusion-based per-view harmonization for lighting-consistent object transfer between 3DGS scenes, using heterogeneous training data and final 3D consolidation.
-
UnsOcc: 3D Semantic Occupancy Prediction in Unstructured Scene via Rendering Fusion
UnsOcc proposes RenderFusion and GSRefinement to improve 3D semantic occupancy prediction in unstructured scenes by enhancing cross-modal fusion and long-tail supervision, outperforming SOTA on a new mine dataset and nuScenes.
-
Gaussian-Voxel Duet: A Dual-Scaffolding Hybrid Representation for Fast and Accurate Monocular Surface Reconstruction
Hybrid Gaussian-voxel scaffolding with surface tethering loss for accurate and efficient monocular 3D surface reconstruction.
-
RT-Splatting: Joint Reflection-Transmission Modeling with Gaussian Splatting
RT-Splatting adds a disentangled occupancy-opacity factorization and specular-aware gradient gating to 3D Gaussian Splatting, enabling joint high-fidelity reflection and transmission in real-time novel view synthesis.
-
Attention Itself Could Retrieve.RetrieveVGGT: Training-Free Long Context Streaming 3D Reconstruction via Query-Key Similarity Retrieval
RetrieveVGGT enables constant-memory long-context streaming 3D reconstruction by retrieving relevant frames via query-key similarities in VGGT's first attention layer, outperforming StreamVGGT and others.
-
LagrangianSplats: Divergence-Free Transport of Gaussian Primitives for Fluid Reconstruction
A framework that structurally enforces divergence-free velocity and long-range transport coherence in 3D fluid reconstruction from 2D videos via divergence-free kernels advecting Lagrangian Gaussian splats.
-
EnerGS: Energy-Based Gaussian Splatting with Partial Geometric Priors
EnerGS introduces an energy-based soft guidance mechanism for partial geometry in 3D Gaussian Splatting to improve reconstruction quality and reduce overfitting in sparse outdoor settings.
-
Light 'em Up: Enabling Few-Shot Low-Light 3D Gaussian Splatting with Multi-Scale Explicit Retinex Illumination Decoupling
MERID-GS decouples illumination and reflectance at multiple scales with learnable gain and frequency gating to support few-shot low-light 3D Gaussian Splatting and cross-scene generalization.
-
Fast Voxelization and Level of Detail for Microgeometry Rendering
A CUDA-parallel voxelizer and hierarchical SGGX clustering representation enable faster, more accurate level-of-detail rendering of sparse microgeometry volumes.
-
BulletGen: Improving 4D Reconstruction with Bullet-Time Generation
BulletGen enhances 4D dynamic scene reconstruction from monocular videos by supervising Gaussian optimization with diffusion-generated frames aligned at a bullet-time step, achieving SOTA on novel-view synthesis and tracking.
-
PREF: Phasorial Embedding Fields for Compact Neural Representations
PREF introduces a phasor volume and tailored Fourier mapping to let shallow MLPs capture high-frequency signals compactly in 2D images, 3D SDFs, and 5D NeRFs.
-
TWINGS: Thin Plate Splines Warp-aligned Initialization for Sparse-View Gaussian Splatting
TWINGS aligns monocular depth backprojections to triangulated 3D control points via thin-plate splines, densifying the initial point cloud and improving sparse-view 3D Gaussian Splatting (e.g., +2.3 dB PSNR over CoR-GS on DTU 3-view).
-
ReorgGS: Equivalent Distribution Reorganization for 3D Gaussian Splatting
ReorgGS reorganizes the Gaussian distribution in converged 3DGS models by resampling centers and covariances to reduce parameterization degeneration and enable better subsequent optimization.
-
Geometry-Aware Scene Configurations for Novel View Synthesis
Geometry-guided adaptive placement of bases and virtual viewpoints improves rendering quality and memory use over uniform arrangements in scalable NeRF for large indoor scenes.
-
CLEAR-NeRF: Collinearity and Local-region Enhanced Accurate 3D Reconstruction in Unbounded Scenes
CLEAR-NeRF augments standard NeRF with four targeted components for superior photorealism and metric accuracy in multi-ROI unbounded scenes compared to baseline NeRF and SfM-MVS methods.
-
NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)
A literature survey of NeRF and neural field methods from 2020-2025, organized by architecture and application taxonomies with benchmarks and dataset overviews, covering both pre- and post-Gaussian Splatting periods.
- PanDORA: Casual HDR Radiance Acquisition of Indoor Scenes for Image-based Lighting