# Evolving High-Quality Rendering and Reconstruction in a Unified Framework with Contribution-Adaptive Regularization arXiv: https://arxiv.org/abs/2503.00881 ยท HTML: https://mlsanity.com/paper/2503.00881/ ## Key facts - Cited by 10 papers in the map (data through 14 Oct 2026). - Builds on 27 of its 35 references that are in the map. - First posted on arXiv 2 Mar 2025. ## Builds on (most cited first, 27 of 27) - [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018) - [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023) - [Instant Neural Graphics Primitives with a Multiresolution Hash Encoding](https://mlsanity.com/paper/2201.05989/) (2022) - [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021) - [Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields](https://mlsanity.com/paper/2103.13415/) (2021) - [NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstruction](https://mlsanity.com/paper/2106.10689/) (2021) - [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021) - [2D Gaussian Splatting for Geometrically Accurate Radiance Fields](https://mlsanity.com/paper/2403.17888/) (2024) - [Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction](https://mlsanity.com/paper/2111.11215/) (2021) - [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020) - [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023) - [KiloNeRF: Speeding up Neural Radiance Fields with Thousands of Tiny MLPs](https://mlsanity.com/paper/2103.13744/) (2021) - [Mip-Splatting: Alias-free 3D Gaussian Splatting](https://mlsanity.com/paper/2311.16493/) (2023) - [UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction](https://mlsanity.com/paper/2104.10078/) (2021) - [SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering](https://mlsanity.com/paper/2311.12775/) (2023) - [Baking Neural Radiance Fields for Real-Time View Synthesis](https://mlsanity.com/paper/2103.14645/) (2021) - [Neuralangelo: High-Fidelity Neural Surface Reconstruction](https://mlsanity.com/paper/2306.03092/) (2023) - [PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction](https://mlsanity.com/paper/2406.06521/) (2024) - [BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis](https://mlsanity.com/paper/2302.14859/) (2023) - [Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction](https://mlsanity.com/paper/2205.15848/) (2022) - [GaussianPro: 3D Gaussian Splatting with Progressive Propagation](https://mlsanity.com/paper/2402.14650/) (2024) - [Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections](https://mlsanity.com/paper/2403.15704/) (2024) - [Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction](https://mlsanity.com/paper/2208.12697/) (2022) - [GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction](https://mlsanity.com/paper/2403.16964/) (2024) - [Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra](https://mlsanity.com/paper/2304.09987/) (2023) - [GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane](https://mlsanity.com/paper/2405.17596/) (2024) - [WE-GS: An In-the-wild Efficient 3D Gaussian Representation for Unconstrained Photo Collections](https://mlsanity.com/paper/2406.02407/) (2024) ## Built on by (most cited first, 10 of 10) - [FastVGGT: Training-Free Acceleration of Visual Geometry Transformer](https://mlsanity.com/paper/2509.02560/) (2025) - [PanoVGGT: Feed-Forward 3D Reconstruction from Panoramic Imagery](https://mlsanity.com/paper/2603.17571/) (2026) - [Training-Free Hierarchical Scene Understanding for Gaussian Splatting with Superpoint Graphs](https://mlsanity.com/paper/2504.13153/) (2025) - [DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion](https://mlsanity.com/paper/2506.21544/) (2025) - [Seg-Wild: Interactive Segmentation based on 3D Gaussian Splatting for Unconstrained Image Collections](https://mlsanity.com/paper/2507.07395/) (2025) - [XSpecMesh: Quality-Preserving Auto-Regressive Mesh Generation Acceleration via Multi-Head Speculative Decoding](https://mlsanity.com/paper/2507.23777/) (2025) - [OmniIndoor3D: Comprehensive Indoor 3D Reconstruction](https://mlsanity.com/paper/2505.20610/) (2025) - [Taking Language Embedded 3D Gaussian Splatting into the Wild](https://mlsanity.com/paper/2507.19830/) (2025) - [Geometry Gaussians: Decoupling Appearance and Geometry in Gaussian Splatting](https://mlsanity.com/paper/2606.05124/) (2026) - [TV-SGS: Gaussian Splatting with Geometric Information Propagation via Tensor Voting under sparse views](https://mlsanity.com/paper/2609.07734/) (2026) ## Abstract (arXiv) Representing 3D scenes from multiview images is a core challenge in computer vision and graphics, which requires both precise rendering and accurate reconstruction. Recently, 3D Gaussian Splatting (3DGS) has garnered significant attention for its high-quality rendering and fast inference speed. Yet, due to the unstructured and irregular nature of Gaussian point clouds, ensuring accurate geometry reconstruction remains difficult. Existing methods primarily focus on geometry regularization, with common approaches including primitive-based and dual-model frameworks. However, the former suffers from inherent conflicts between rendering and reconstruction, while the latter is computationally and storage-intensive. To address these challenges, we propose CarGS, a unified model leveraging Contribution-adaptive regularization to achieve simultaneous, high-quality rendering and surface reconstruction. The essence of our framework is learning adaptive contribution for Gaussian primitives by squeezing the knowledge from geometry regularization into a compact MLP. Additionally, we introduce a geometry-guided densification strategy with clues from both normals and Signed Distance Fields (SDF) to improve the capability of capturing high-frequency details. Our design improves the mutual learning of the two tasks, meanwhile its unified structure does not require separate models as in dual-model based approaches, guaranteeing efficiency. Extensive experiments demonstrate the ability to achieve state-of-the-art (SOTA) results in both rendering fidelity and reconstruction accuracy while maintaining real-time speed and minimal storage size.