mlsanityData to 7 Oct 2026

ConFixGS: Learning to Fix Feedforward 3D Gaussian Splatting with Confidence-Aware Diffusion Priors in Driving Scenes

arXiv 2605.09688 ↗First posted 10 May 2026cs.CVcited by 0

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

Feedforward 3D Gaussian Splatting (3DGS) often struggles in trajectory-based sparse-view driving scenes. Existing Gaussian repair methods mainly target optimization-based 3DGS, while diffusion-based repair is typically restricted to iterative refinement near observed viewpoints, leaving feedforward 3DGS repair underexplored. We propose ConFixGS, a plug-and-play method that learns to fix feedforward 3DGS with confidence-aware diffusion priors. Starting from a pretrained feedforward model, ConFixGS generates diffusion-enhanced local pseudo-targets and validates them through reprojection-based cross-checking against support views. The resulting dense confidence maps guide refinement, enhancing reliable details while suppressing hallucinated or inconsistent evidence. On Waymo, nuScenes, and KITTI, ConFixGS improves challenging novel view synthesis, with PSNR gains of up to 3.68 dB and FID reduced by nearly half. Our results highlight confidence-aware fusion of generative priors and support-view consistency as a key principle for robust feedforward 3D driving scene reconstruction.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 98 of its 105 references that are in the map. First posted on arXiv 10 May 2026.

Builds on

98 of 105 references.

Closest ancestors · 14

Same direction, newest first

  1. 2025FixingGS: Enhancing 3D Gaussian Splatting via Training-Free Score Distillation23 Sep
  2. 2025GSFix3D: Diffusion-Guided Repair of Novel Views in Gaussian Splatting20 Aug
  3. 2025GSFixer: Improving 3D Gaussian Splatting with Reference-Guided Video Diffusion Priors13 Aug
  4. 2025RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors13 Mar
  5. 2025TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models7 Mar
  6. 2025Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models3 Mar
  7. 20243DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors21 Oct
  8. 2024LM-Gaussian: Boost Sparse-view 3D Gaussian Splatting with Large Model Priors5 Sep
  9. 2024MultiDiff: Consistent Novel View Synthesis from a Single Image26 Jun
  10. 2024Score Distillation Sampling with Learned Manifold Corrective10 Jan
  11. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Image7 Sep
  12. 2023MVDream: Multi-view Diffusion for 3D Generation31 Aug
2 more
  1. 2023HoloFusion: Towards Photo-realistic 3D Generative Modeling28 Aug
  2. 2023Zero-1-to-3: Zero-shot One Image to 3D Object20 Mar

Other references · 84

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  4. 2022InstructPix2Pix: Learning to Follow Image Editing Instructionscited by 2,591
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,013
  7. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,957
  8. 2018Towards Accurate Generative Models of Video: A New Metric & Challengescited by 1,204
  9. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,144
  10. 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,061
  11. 2020NeRF++: Analyzing and Improving Neural Radiance Fieldscited by 857
  12. 2023Adversarial Diffusion Distillationcited by 741
38 more
  1. 2024LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creationcited by 730
  2. 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 684
  3. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 668
  4. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 661
  5. 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 611
  6. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 553
  7. 2023Instruct-NeRF2NeRF: Editing 3D Scenes with Instructionscited by 482
  8. 2023DrivingGaussian: Composite Gaussian Splatting for Surrounding Dynamic Autonomous Driving Scenescited by 359
  9. 2024GS-LRM: Large Reconstruction Model for 3D Gaussian Splattingcited by 344
  10. 2024PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstructioncited by 280
  11. 2024DepthSplat: Connecting Gaussian Splatting and Depthcited by 275
  12. 2022DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detectioncited by 270
  13. 2023Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformerscited by 257
  14. 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
  15. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 241
  16. 2017A General and Adaptive Robust Loss Functioncited by 236
  17. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 234
  18. 2019MOTS: Multi-Object Tracking and Segmentationcited by 222
  19. 2016Generating Images with Perceptual Similarity Metrics based on Deep Networkscited by 221
  20. 2024Street Gaussians: Modeling Dynamic Urban Scenes with Gaussian Splattingcited by 218
  21. 2023EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervisioncited by 216
  22. 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 199
  23. 2024Taming 3DGS: High-Quality Radiance Fields with Limited Resourcescited by 198
  24. 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusioncited by 179
  25. 2023Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Imagescited by 172
  26. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 171
  27. 2023V2V4Real: A Real-world Large-scale Dataset for Vehicle-to-Vehicle Cooperative Perceptioncited by 155
  28. 2025Pseudo-Simulation for Autonomous Drivingcited by 141
  29. 2024DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshingcited by 136
  30. 2023StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Viewscited by 120
  31. 2024latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstructioncited by 114
  32. 2024MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Viewscited by 111
  33. 2024FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenescited by 86
  34. 2024HUGSIM: A Real-Time, Photo-Realistic and Closed-Loop Simulator for Autonomous Drivingcited by 84
  35. 2024GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warpingcited by 72
  36. 2024TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformerscited by 71
  37. 2024TUMTraf V2X Cooperative Perception Datasetcited by 66
  38. 2024SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Drivingcited by 66

50 most cited of 84 All 84 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025RGE-GS: Reward-Guided Expansive Driving Scene Reconstruction via Diffusion Priors
  2. 2026OneFixer: High-Quality and Consistent One-Step Autoregressive 3DGS Refinement for Driving Scenes
  3. 2025Taming Video Diffusion Prior with Scene-Grounding Guidance for 3D Gaussian Splatting from Sparse Inputs
  4. 2026GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Views
  5. 2026PRG-Fusion: Orchestrating Generative Priors with Reconstruction Evidence for Driving View Synthesis
  6. 2025OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting
  7. 2026GaussVid: Sparse-View Gaussian Splatting with 3D-Aware Video Diffusion Priors
  8. 2026DensiTok: Making Feed-Forward 3D Gaussian Splatting See More Views Than It Is Given