# 3D-RelNet: Joint Object and Relational Network for 3D Prediction

arXiv: https://arxiv.org/abs/1906.02729 · HTML: https://mlsanity.com/paper/1906.02729/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2019.

## Built on by (most cited first, 28 of 28)

- [Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild](https://mlsanity.com/paper/2207.10660/) (2022)
- [ROCA: Robust CAD Model Retrieval and Alignment from a Single Image](https://mlsanity.com/paper/2112.01988/) (2021)
- [Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View](https://mlsanity.com/paper/2404.03421/) (2024)
- [Few-View Object Reconstruction with Unknown Categories and Camera Poses](https://mlsanity.com/paper/2212.04492/) (2022)
- [Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes](https://mlsanity.com/paper/2207.08656/) (2022)
- [Planar Surface Reconstruction from Sparse Views](https://mlsanity.com/paper/2103.14644/) (2021)
- [D3D-HOI: Dynamic 3D Human-Object Interactions from Videos](https://mlsanity.com/paper/2108.08420/) (2021)
- [Understanding 3D Object Articulation in Internet Videos](https://mlsanity.com/paper/2203.16531/) (2022)
- [Compositional Scene Representation Learning via Reconstruction: A Survey](https://mlsanity.com/paper/2202.07135/) (2022)
- [3DP3: 3D Scene Perception via Probabilistic Programming](https://mlsanity.com/paper/2111.00312/) (2021)
- [3DiffTection: 3D Object Detection with Geometry-Aware Diffusion Features](https://mlsanity.com/paper/2311.04391/) (2023)
- [Virtual Correspondence: Humans as a Cue for Extreme-View Geometry](https://mlsanity.com/paper/2206.08365/) (2022)
- [Bending Graphs: Hierarchical Shape Matching using Gated Optimal Transport](https://mlsanity.com/paper/2202.01537/) (2022)
- [Monte Carlo Scene Search for 3D Scene Understanding](https://mlsanity.com/paper/2103.07969/) (2021)
- [RelationField: Relate Anything in Radiance Fields](https://mlsanity.com/paper/2412.13652/) (2024)
- [ARM3D: Attention-based relation module for indoor 3D object detection](https://mlsanity.com/paper/2202.09715/) (2022)
- [IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes](https://mlsanity.com/paper/2112.05298/) (2021)
- [Coherent 3D Scene Diffusion From a Single RGB Image](https://mlsanity.com/paper/2412.10294/) (2024)
- [What's Behind the Couch? Directed Ray Distance Functions (DRDF) for 3D Scene Reconstruction](https://mlsanity.com/paper/2112.04481/) (2021)
- [3DFIRES: Few Image 3D REconstruction for Scenes with Hidden Surface](https://mlsanity.com/paper/2403.08768/) (2024)
- [V-MIND: Building Versatile Monocular Indoor 3D Detector with Diverse 2D Annotations](https://mlsanity.com/paper/2412.11412/) (2024)
- [GeoScaler: Geometry and Rendering-Aware Downsampling of 3D Mesh Textures](https://mlsanity.com/paper/2311.16581/) (2023)
- [Learning to Predict Scene-Level Implicit 3D from Posed RGBD Data](https://mlsanity.com/paper/2306.08671/) (2023)
- [CatFree3D: Category-agnostic 3D Object Detection with Diffusion](https://mlsanity.com/paper/2408.12747/) (2024)
- [3DRM:Pair-wise relation module for 3D object detection](https://mlsanity.com/paper/2202.09721/) (2022)
- [Review on 6D Object Pose Estimation with the focus on Indoor Scene Understanding](https://mlsanity.com/paper/2212.01920/) (2022)
- [Explicit3D: Graph Network with Spatial Inference for Single Image 3D Object Detection](https://mlsanity.com/paper/2302.06494/) (2023)
- [Single-image coherent reconstruction of objects and humans](https://mlsanity.com/paper/2408.08086/) (2024)

## Abstract (arXiv)

We propose an approach to predict the 3D shape and pose for the objects present in a scene. Existing learning based methods that pursue this goal make independent predictions per object, and do not leverage the relationships amongst them. We argue that reasoning about these relationships is crucial, and present an approach to incorporate these in a 3D prediction framework. In addition to independent per-object predictions, we predict pairwise relations in the form of relative 3D pose, and demonstrate that these can be easily incorporated to improve object level estimates. We report performance across different datasets (SUNCG, NYUv2), and show that our approach significantly improves over independent prediction approaches while also outperforming alternate implicit reasoning methods.