Data to 14 Oct 2026

SDFDiff: Differentiable Rendering of Signed Distance Fields for 3D Shape Optimization

arXiv 1912.07109 ↗First posted 15 Dec 2019cs.CV cs.GR cs.LGcited by 159

Not on the map. Why?

Abstract (arXiv)

We propose SDFDiff, a novel approach for image-based shape optimization using differentiable rendering of 3D shapes represented by signed distance functions (SDFs). Compared to other representations, SDFs have the advantage that they can represent shapes with arbitrary topology, and that they guarantee watertight surfaces. We apply our approach to the problem of multi-view 3D reconstruction, where we achieve high reconstruction quality and can capture complex topology of 3D objects. In addition, we employ a multi-resolution strategy to obtain a robust optimization algorithm. We further demonstrate that our SDF-based differentiable renderer can be integrated with deep learning models, which opens up options for learning approaches on 3D objects without 3D supervision. In particular, we apply our method to single-view 3D reconstruction and achieve state-of-the-art results.

Key facts. Cited by 159 papers in the map (data through 14 Oct 2026). First posted on arXiv 15 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 38; 2022: 42; 2023: 45; 2024: 20; 2025: 11; 2026: 3.

159 papers.

Sort:

By area:

2021NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Multi-view Reconstructioncited by 1,712
2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
2021RegNeRF: Regularizing Neural Radiance Fields for View Synthesis from Sparse Inputscited by 615
2022MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstructioncited by 470
2023Neuralangelo: High-Fidelity Neural Surface Reconstructioncited by 467
2021Neural Geometric Level of Detail: Real-time Rendering with Implicit 3D Shapescited by 426
2021Extracting Triangular 3D Models, Materials, and Lighting From Imagescited by 366
2021Advances in Neural Renderingcited by 365
2021PhySG: Inverse Rendering with Spherical Gaussians for Physics-based Material Editing and Relightingcited by 335
2023OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generationcited by 326
2022NeuS2: Fast Learning of Neural Implicit Surfaces for Multi-view Reconstructioncited by 314

38 more

2022SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generationcited by 288
20223D Neural Field Generation using Triplane Diffusioncited by 274
2021HeadNeRF: A Real-time NeRF-based Parametric Head Modelcited by 228
2022AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generationcited by 208
2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 177
2021SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformercited by 164
2022Dream3D: Zero-Shot Text-to-3D Synthesis Using 3D Shape Prior and Text-to-Image Diffusion Modelscited by 151
2021Efficient Neural Radiance Fields for Interactive Free-viewpoint Videocited by 150
2022SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Videocited by 144
2021BACON: Band-limited Coordinate Networks for Multiscale Scene Representationcited by 143
2021Real-time Deep Dynamic Characterscited by 133
2022Diffusion-SDF: Text-to-Shape via Voxelized Diffusioncited by 128
2022iSDF: Real-Time Neural Signed Distance Fields for Robot Perceptioncited by 109
2021Neural Lumigraph Renderingcited by 105
2022Generative Neural Articulated Radiance Fieldscited by 101
2022Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstructioncited by 94
20234K4D: Real-Time 4D View Synthesis at 4K Resolutioncited by 91
20243DGSR: Implicit Surface Reconstruction with 3D Gaussian Splattingcited by 79
2021DiGS : Divergence guided shape implicit neural representation for unoriented point cloudscited by 77
2022PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Latticescited by 73
2021Unified Shape and SVBRDF Recovery using Differentiable Monte Carlo Renderingcited by 71
2022Unified Implicit Neural Stylizationcited by 67
2021ACORN: Adaptive Coordinate Networks for Neural Scene Representationcited by 65
2021Compressive Neural Representations of Volumetric Scalar Fieldscited by 64
2022NeuralUDF: Learning Unsigned Distance Fields for Multi-view Reconstruction of Surfaces with Arbitrary Topologiescited by 63
2021CAPRI-Net: Learning Compact CAD Shapes with Adaptive Primitive Assemblycited by 62
2022Reconstructing Surfaces for Sparse Point Clouds with On-Surface Priorscited by 60
2022PMP-Net++: Point Cloud Completion by Transformer-Enhanced Multi-step Point Moving Pathscited by 57
2023Im4D: High-Fidelity and Real-Time Novel View Synthesis for Dynamic Scenescited by 55
2022Surface Reconstruction from Point Clouds by Learning Predictive Context Priorscited by 54
2023Cross-Ray Neural Radiance Fields for Novel-view Synthesis from Unconstrained Image Collectionscited by 54
2021DoubleField: Bridging the Neural Surface and Radiance Fields for High-fidelity Human Reconstruction and Renderingcited by 52
2021Generative Occupancy Fields for 3D Surface-Aware Image Synthesiscited by 51
2021Cycle4Completion: Unpaired Point Cloud Completion using Cycle Transformation with Missing Region Codingcited by 50
2022CAP-UDF: Learning Unsigned Distance Functions Progressively from Raw Point Clouds with Consistency-Aware Field Optimizationcited by 47
2024When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Modelscited by 43
2022A Level Set Theory for Neural Implicit Evolution under Explicit Flowscited by 42
2023MixNeRF: Modeling a Ray with Mixture Density for Novel View Synthesis from Sparse Inputscited by 40

50 most cited of 159 All 159 (JSON)