# DPF: Learning Dense Prediction Fields with Weak Supervision

arXiv: https://arxiv.org/abs/2303.16890 · HTML: https://mlsanity.com/paper/2303.16890/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 73 references that are in the map.
- First posted on arXiv 29 Mar 2023.

## Builds on (most cited first, 30 of 46)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation](https://mlsanity.com/paper/1901.05103/) (2019)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Vision Transformers for Dense Prediction](https://mlsanity.com/paper/2103.13413/) (2021)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Learning Continuous Image Representation with Local Implicit Image Function](https://mlsanity.com/paper/2012.09161/) (2020)
- [What's the Point: Semantic Segmentation with Point Supervision](https://mlsanity.com/paper/1506.02106/) (2015)
- [Learning Shape Templates with Structured Implicit Functions](https://mlsanity.com/paper/1904.06447/) (2019)
- [Inverse Rendering for Complex Indoor Scenes: Shape, Spatially-Varying Lighting and SVBRDF from a Single Image](https://mlsanity.com/paper/1905.02722/) (2019)
- [Object Region Mining with Adversarial Erasing: A Simple Classification to Semantic Segmentation Approach](https://mlsanity.com/paper/1703.08448/) (2017)
- [SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis](https://mlsanity.com/paper/1708.01749/) (2017)
- [Neural Inverse Rendering of an Indoor Scene from a Single Image](https://mlsanity.com/paper/1901.02453/) (2019)
- [CGIntrinsics: Better Intrinsic Image Decomposition through Physically-Based Rendering](https://mlsanity.com/paper/1808.08601/) (2018)
- [Deep Parametric Indoor Lighting Estimation](https://mlsanity.com/paper/1910.08812/) (2019)
- [STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation](https://mlsanity.com/paper/1509.03150/) (2015)
- [Rendering Synthetic Objects into Legacy Photographs](https://mlsanity.com/paper/1912.11565/) (2019)
- [FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation](https://mlsanity.com/paper/1903.11816/) (2019)
- [Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image](https://mlsanity.com/paper/1808.02201/) (2018)
- [IRISformer: Dense Vision Transformers for Single-Image Inverse Rendering in Indoor Scenes](https://mlsanity.com/paper/2206.08423/) (2022)
- [Neural Illumination: Lighting Prediction for Indoor Environments](https://mlsanity.com/paper/1906.07370/) (2019)
- [Unsupervised Learning for Intrinsic Image Decomposition from a Single Image](https://mlsanity.com/paper/1911.09930/) (2019)
- [Self-Supervised Intrinsic Image Decomposition](https://mlsanity.com/paper/1711.03678/) (2017)
- [STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation](https://mlsanity.com/paper/2302.01334/) (2023)
- [Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression](https://mlsanity.com/paper/1512.02311/) (2015)
- [LIME: Live Intrinsic Material Estimation](https://mlsanity.com/paper/1801.01075/) (2018)
- [Weakly Supervised Scene Parsing with Point-based Distance Metric Learning](https://mlsanity.com/paper/1811.02233/) (2018)
- [Joint Implicit Image Function for Guided Depth Super-Resolution](https://mlsanity.com/paper/2107.08717/) (2021)
- [Learning Implicit Feature Alignment Function for Semantic Segmentation](https://mlsanity.com/paper/2206.08655/) (2022)

## Built on by (most cited first, 3 of 3)

- [Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images](https://mlsanity.com/paper/2402.05869/) (2024)
- [InvRGB+L: Inverse Rendering of Complex Scenes with Unified Color and LiDAR Reflectance Modeling](https://mlsanity.com/paper/2507.17613/) (2025)
- [LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditions](https://mlsanity.com/paper/2602.01118/) (2026)

## Abstract (arXiv)

Nowadays, many visual scene understanding problems are addressed by dense prediction networks. But pixel-wise dense annotations are very expensive (e.g., for scene parsing) or impossible (e.g., for intrinsic image decomposition), motivating us to leverage cheap point-level weak supervision. However, existing pointly-supervised methods still use the same architecture designed for full supervision. In stark contrast to them, we propose a new paradigm that makes predictions for point coordinate queries, as inspired by the recent success of implicit representations, like distance or radiance fields. As such, the method is named as dense prediction fields (DPFs). DPFs generate expressive intermediate features for continuous sub-pixel locations, thus allowing outputs of an arbitrary resolution. DPFs are naturally compatible with point-level supervision. We showcase the effectiveness of DPFs using two substantially different tasks: high-level semantic parsing and low-level intrinsic image decomposition. In these two cases, supervision comes in the form of single-point semantic category and two-point relative reflectance, respectively. As benchmarked by three large-scale public datasets PASCALContext, ADE20K and IIW, DPFs set new state-of-the-art performance on all of them with significant margins. Code can be accessed at https://github.com/cxx226/DPF.