awesome-implicit-representations
github.com/vsitzmann/awesome-implicit-representations ↗A curated list of resources on implicit neural representations.
2.6k
GitHub Stars
64
Curated Resources
16
Categories
55 min ago
Last Refreshed
DisclaimerWhy are they interesting?Implicit Neural Representations of GeometryImplicit representations of Geometry and AppearanceSymmetries in Implicit Neural RepresentationsHybrid implicit / explicit (condition implicit on local features)Learning correspondence with Neural Implicit RepresentationsRobotics ApplicationsGeneralization & Meta-Learning with Neural Implicit RepresentationsFitting high-frequency detail with positional encoding & periodic nonlinearitiesImplicit Neural Representations of ImagesComposing implicit neural representationsImplicit Representations for Partial Differential Equations & Boundary Value ProblemsGenerative Adverserial Networks with Implicit RepresentationsImage-to-image translationArticulated representations
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me for 2d resources from awesome-implicit-representations"
Installation instructions →What's inside
Robotics Applications
Generative Adverserial Networks with Implicit Representations
- Adversarial Generation of Continuous ImagesFor 2D
- Alias-Free GANFor 2D
- Alias-Free Generative Adversarial Networks (StyleGAN3)For 3D
- Generative Radiance Fields for 3D-Aware Image SynthesisFor 3D
- Image Generators with Conditionally-Independent Pixel SynthesisFor 2D
- Learning Continuous Image Representation with Local Implicit Image FunctionFor 2D
Articulated representations
- Andreas Geiger: Neural Implicit Representations for 3D Vision (Occupancy Networks, Texture Fields, Occupancy Flow, Differentiable Volumetric Rendering, GRAF)
- awesome-NeRF
List of implicit representations specifically on neural radiance fields (NeRF)
- Gerard Pons-Moll: Shape Representations: Parametric Meshes vs Implicit Functions
- NASA: Neural Articulated Shape Approximation
- Vincent Sitzmann: Implicit Neural Scene Representations (Scene Representation Networks, MetaSDF, Semantic Segmentation with Implicit Neural Representations, SIREN)
- Yaron Lipman: Implicit Neural Representations
Implicit Representations for Partial Differential Equations & Boundary Value Problems
Implicit Neural Representations of Images
Hybrid implicit / explicit (condition implicit on local features)
- Convolutional Occupancy Networks
- Deep Local Shapes: Learning Local SDF Priors for Detailed 3D Reconstruction
- Implicit Functions in Feature Space for 3D ShapeReconstruction and Completion
- Local Deep Implicit Functions for 3D Shape
- Local Implicit Grid Representations for 3D Scenes
- Neural Sparse Voxel Fields
Implicit Neural Representations of Geometry
- DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
- IM-Net: Learning Implicit Fields for Generative Shape Modeling
- Neural Unsigned Distance Fields for Implicit Function Learning
- Occupancy Networks: Learning 3D Reconstruction in Function Space
- Sal: Sign agnostic learning of shapes from raw data
Implicit representations of Geometry and Appearance
- Deformable Neural Radiance FieldsFor dynamic scenes
- Differentiable volumetric rendering: Learning implicit 3d representations without 3d supervisionFrom 2D supervision only (“inverse graphics”)
- D-NeRF: Neural Radiance Fields for Dynamic ScenesFor dynamic scenes
- Light Field Networks: Neural Scene Representations with Single-Evaluation RenderingFrom 2D supervision only (“inverse graphics”)
- Multiview neural surface reconstruction by disentangling geometry and appearanceFrom 2D supervision only (“inverse graphics”)
- Neural Radiance Flow for 4D View Synthesis and Video ProcessingFor dynamic scenes
Showing a sample of 64 resources. View the full list on GitHub →