# D2IM-Net: Learning Detail Disentangled Implicit Fields from Single Images

arXiv: https://arxiv.org/abs/2012.06650 · HTML: https://mlsanity.com/paper/2012.06650/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2020.

## Built on by (most cited first, 30 of 42)

- [Deep Marching Tetrahedra: a Hybrid Representation for High-Resolution 3D Shape Synthesis](https://mlsanity.com/paper/2111.04276/) (2021)
- [Neural Wavelet-domain Diffusion for 3D Shape Generation](https://mlsanity.com/paper/2209.08725/) (2022)
- [HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details](https://mlsanity.com/paper/2206.07850/) (2022)
- [Towards Implicit Text-Guided 3D Shape Generation](https://mlsanity.com/paper/2203.14622/) (2022)
- [Geometry-Consistent Neural Shape Representation with Implicit Displacement Fields](https://mlsanity.com/paper/2106.05187/) (2021)
- [Neural Template: Topology-aware Reconstruction and Disentangled Generation of 3D Meshes](https://mlsanity.com/paper/2206.04942/) (2022)
- [Neural Wavelet-domain Diffusion for 3D Shape Generation, Inversion, and Manipulation](https://mlsanity.com/paper/2302.00190/) (2023)
- [ANISE: Assembly-based Neural Implicit Surface rEconstruction](https://mlsanity.com/paper/2205.13682/) (2022)
- [Cross-domain Compositing with Pretrained Diffusion Models](https://mlsanity.com/paper/2302.10167/) (2023)
- [Slice3D: Multi-Slice, Occlusion-Revealing, Single View 3D Reconstruction](https://mlsanity.com/paper/2312.02221/) (2023)
- [DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image](https://mlsanity.com/paper/2309.12594/) (2023)
- [Object Wake-up: 3D Object Rigging from a Single Image](https://mlsanity.com/paper/2108.02708/) (2021)
- [PatchRD: Detail-Preserving Shape Completion by Learning Patch Retrieval and Deformation](https://mlsanity.com/paper/2207.11790/) (2022)
- [Deformable Model-Driven Neural Rendering for High-Fidelity 3D Reconstruction of Human Heads Under Low-View Settings](https://mlsanity.com/paper/2303.13855/) (2023)
- [LIST: Learning Implicitly from Spatial Transformers for Single-View 3D Reconstruction](https://mlsanity.com/paper/2307.12194/) (2023)
- [SweepNet: Unsupervised Learning Shape Abstraction via Neural Sweepers](https://mlsanity.com/paper/2407.06305/) (2024)
- [Parameterization-driven Neural Surface Reconstruction for Object-oriented Editing in Neural Rendering](https://mlsanity.com/paper/2310.05524/) (2023)
- [VPFusion: Joint 3D Volume and Pixel-Aligned Feature Fusion for Single and Multi-view 3D Reconstruction](https://mlsanity.com/paper/2203.07553/) (2022)
- [A Review of Deep Learning-Powered Mesh Reconstruction Methods](https://mlsanity.com/paper/2303.02879/) (2023)
- [Attention-based Part Assembly for 3D Volumetric Shape Modeling](https://mlsanity.com/paper/2304.10986/) (2023)
- [ARO-Net: Learning Implicit Fields from Anchored Radial Observations](https://mlsanity.com/paper/2212.10275/) (2022)
- [Self-supervised Adaptive Pre-training of Multilingual Speech Models for Language and Dialect Identification](https://mlsanity.com/paper/2312.07338/) (2023)
- [Neural Implicit 3D Shapes from Single Images with Spatial Patterns](https://mlsanity.com/paper/2106.03087/) (2021)
- [Signal Transformer: Complex-valued Attention and Meta-Learning for Signal Recognition](https://mlsanity.com/paper/2106.04392/) (2021)
- [Inferring Implicit 3D Representations from Human Figures on Pictorial Maps](https://mlsanity.com/paper/2209.02385/) (2022)
- [Analysis of Sampling Strategies for Implicit 3D Reconstruction](https://mlsanity.com/paper/2304.03999/) (2023)
- [Pix2Repair: Implicit Shape Restoration from Images](https://mlsanity.com/paper/2305.18273/) (2023)
- [Enhancing Multilingual Speech Recognition through Language Prompt Tuning and Frame-Level Language Adapter](https://mlsanity.com/paper/2309.09443/) (2023)
- [GMTR: Graph Matching Transformers](https://mlsanity.com/paper/2311.08141/) (2023)
- [DarkShot: Lighting Dark Images with Low-Compute and High-Quality](https://mlsanity.com/paper/2312.16805/) (2023)

## Abstract (arXiv)

We present the first single-view 3D reconstruction network aimed at recovering geometric details from an input image which encompass both topological shape structures and surface features. Our key idea is to train the network to learn a detail disentangled reconstruction consisting of two functions, one implicit field representing the coarse 3D shape and the other capturing the details. Given an input image, our network, coined D2IM-Net, encodes it into global and local features which are respectively fed into two decoders. The base decoder uses the global features to reconstruct a coarse implicit field, while the detail decoder reconstructs, from the local features, two displacement maps, defined over the front and back sides of the captured object. The final 3D reconstruction is a fusion between the base shape and the displacement maps, with three losses enforcing the recovery of coarse shape, overall structure, and surface details via a novel Laplacian term.