RouteBridge: Reliability-Routed Bidirectional Distillation Between Neural Radiance Fields and 3D Gaussian Splatting
On the map: Knowledge distillation → Detection and dense prediction distillation
Abstract (arXiv)
Neural radiance fields (NeRFs) and 3D Gaussian Splatting (3DGS) encode a scene with complementary inductive biases, but existing cross-representation distillation typically fixes one representation as teacher for the entire scene. A globally fixed teacher can propagate local reconstruction errors. We present RouteBridge, a bidirectional framework that selects the teaching direction for each ray. Its reliability estimator combines photometric residuals with representation-specific geometric evidence and routes supervision from NeRF to 3DGS, from 3DGS to NeRF, or abstains. A renderer-independent interface transfers color, opacity, and normalized depth without shared features or point correspondence. On mip-NeRF 360, the NeRF and 3DGS exports reach 28.56 and 28.77 dB, respectively. The 3DGS export improves over 3DGS by 1.56 dB and over NeRF-GS by 0.45 dB while reducing LPIPS to 0.207. On static three-view DTU, RouteBridge obtains 21.12 dB. Ablations show that both adaptive routing and geometric ray targets contribute to the improvement.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation. Builds on 57 of its 66 references that are in the map. First posted on arXiv 9 Sep 2026.
Builds on
57 of 66 references.
References · 57
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
- 2022Instant Neural Graphics Primitives with a Multiresolution Hash Encodingcited by 3,723
- 2021Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fieldscited by 2,032
- 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
- 2021Plenoxels: Radiance Fields without Neural Networkscited by 1,613
- 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
- 2020D-NeRF: Neural Radiance Fields for Dynamic Scenescited by 1,465
- 2022TensoRF: Tensorial Radiance Fieldscited by 1,280
- 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
- 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
- 20242D Gaussian Splatting for Geometrically Accurate Radiance Fieldscited by 1,076
38 more
- 2021PlenOctrees for Real-time Rendering of Neural Radiance Fieldscited by 905
- 2023Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstructioncited by 759
- 2021Depth-supervised NeRF: Fewer Views and Faster Training for Freecited by 735
- 2023Scaffold-GS: Structured 3D Gaussians for View-Adaptive Renderingcited by 695
- 2021KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPscited by 673
- 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
- 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
- 2017Deep Mutual Learningcited by 628
- 2023SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Renderingcited by 616
- 2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
- 2023LERF: Language Embedded Radiance Fieldscited by 543
- 2022Point-NeRF: Point-based Neural Radiance Fieldscited by 503
- 2021Baking Neural Radiance Fields for Real-Time View Synthesiscited by 468
- 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
- 2023LangSplat: 3D Language Gaussian Splattingcited by 415
- 2023Compact 3D Gaussian Representation for Radiance Fieldcited by 372
- 2023Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fieldscited by 364
- 2023Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesiscited by 344
- 2022MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architecturescited by 311
- 2023FreeNeRF: Improving Few-shot Neural Rendering with Free Frequency Regularizationcited by 311
- 2024DNGaussian: Optimizing Sparse-View 3D Gaussian Radiance Fields with Global-Local Depth Normalizationcited by 256
- 2023Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesiscited by 239
- 20243D Gaussian Splatting as Markov Chain Monte Carlocited by 217
- 2024VastGaussian: Vast 3D Gaussians for Large Scene Reconstructioncited by 209
- 2024GaussianPro: 3D Gaussian Splatting with Progressive Propagationcited by 200
- 2021InfoNeRF: Ray Entropy Minimization for Few-Shot Neural Volume Renderingcited by 182
- 2023Multi-Scale 3D Gaussian Splatting for Anti-Aliased Renderingcited by 138
- 2024RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPScited by 113
- 2024Pixel-GS: Density Control with Pixel-aware Gradient for 3D Gaussian Splattingcited by 113
- 2024StopThePop: Sorted Gaussian Splatting for View-Consistent Real-time Renderingcited by 111
- 2024RaDe-GS: Rasterizing Depth in Gaussian Splattingcited by 111
- 2024SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstructioncited by 52
- 2023Gaussian Splatting with NeRF-based Color and Opacitycited by 30
- 2023HybridNeRF: Efficient Neural Rendering via Adaptive Volumetric Surfacescited by 28
- 2023Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splattingcited by 20
- 2024Chat-Edit-3D: Interactive 3D Scene Editing via Text Promptscited by 19
- 2022One is All: Bridging the Gap Between Neural Radiance Fields Architectures with Progressive Volume Distillationcited by 18
- 2025NeRF Is a Valuable Assistant for 3D Gaussian Splattingcited by 15
50 most cited of 57 All 57 (JSON)
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Divide and Conquer: Rethinking the Training Paradigm of Neural Radiance Fields
- 2026LightBridge: Feed-Forward Generative Relighting for 3D Gaussian Splatting
- 2024ID-NeRF: Indirect Diffusion-guided Neural Radiance Fields for Generalizable View Synthesis
- 2023NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion
- 2025Diffusion-Guided Gaussian Splatting for Large-Scale Unconstrained 3D Reconstruction and Novel View Synthesis
- 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction
- 2024Omni-Recon: Harnessing Image-based Rendering for General-Purpose Neural Radiance Fields
- 2026MLP Splatting: Object-Centric Neural Fields