# ADOP: Approximate Differentiable One-Pixel Point Rendering

arXiv: https://arxiv.org/abs/2110.06635 · HTML: https://mlsanity.com/paper/2110.06635/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 61 of its 103 references that are in the map.
- First posted on arXiv 13 Oct 2021.

## Builds on (most cited first, 30 of 61)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (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)
- [Occupancy Networks: Learning 3D Reconstruction in Function Space](https://mlsanity.com/paper/1812.03828/) (2018)
- [pixelNeRF: Neural Radiance Fields from One or Few Images](https://mlsanity.com/paper/2012.02190/) (2020)
- [NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections](https://mlsanity.com/paper/2008.02268/) (2020)
- [NeRF++: Analyzing and Improving Neural Radiance Fields](https://mlsanity.com/paper/2010.07492/) (2020)
- [ORB-SLAM2: an Open-Source SLAM System for Monocular, Stereo and RGB-D Cameras](https://mlsanity.com/paper/1610.06475/) (2016)
- [Accelerating 3D Deep Learning with PyTorch3D](https://mlsanity.com/paper/2007.08501/) (2020)
- [Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision](https://mlsanity.com/paper/1912.07372/) (2019)
- [Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines](https://mlsanity.com/paper/1905.00889/) (2019)
- [BARF: Bundle-Adjusting Neural Radiance Fields](https://mlsanity.com/paper/2104.06405/) (2021)
- [Free-Form Image Inpainting with Gated Convolution](https://mlsanity.com/paper/1806.03589/) (2018)
- [Empirical Evaluation of Rectified Activations in Convolutional Network](https://mlsanity.com/paper/1505.00853/) (2015)
- [Direct Sparse Odometry](https://mlsanity.com/paper/1607.02565/) (2016)
- [Neural 3D Mesh Renderer](https://mlsanity.com/paper/1711.07566/) (2017)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [DeepVoxels: Learning Persistent 3D Feature Embeddings](https://mlsanity.com/paper/1812.01024/) (2018)
- [SynSin: End-to-end View Synthesis from a Single Image](https://mlsanity.com/paper/1912.08804/) (2019)
- [Neural Point-Based Graphics](https://mlsanity.com/paper/1906.08240/) (2019)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [State of the Art on Neural Rendering](https://mlsanity.com/paper/2004.03805/) (2020)
- [Single-View View Synthesis with Multiplane Images](https://mlsanity.com/paper/2004.11364/) (2020)
- [Deferred Neural Rendering: Image Synthesis using Neural Textures](https://mlsanity.com/paper/1904.12356/) (2019)
- [Differentiable Surface Splatting for Point-based Geometry Processing](https://mlsanity.com/paper/1906.04173/) (2019)
- [Free View Synthesis](https://mlsanity.com/paper/2008.05511/) (2020)
- [Learning to Predict 3D Objects with an Interpolation-based Differentiable Renderer](https://mlsanity.com/paper/1908.01210/) (2019)

## Built on by (most cited first, 9 of 9)

- [Plenoxels: Radiance Fields without Neural Networks](https://mlsanity.com/paper/2112.05131/) (2021)
- [HDR-NeRF: High Dynamic Range Neural Radiance Fields](https://mlsanity.com/paper/2111.14451/) (2021)
- [Differentiable Point-Based Radiance Fields for Efficient View Synthesis](https://mlsanity.com/paper/2205.14330/) (2022)
- [Neural Point Catacaustics for Novel-View Synthesis of Reflections](https://mlsanity.com/paper/2301.01087/) (2023)
- [Watch It Move: Unsupervised Discovery of 3D Joints for Re-Posing of Articulated Objects](https://mlsanity.com/paper/2112.11347/) (2021)
- [HDR-Plenoxels: Self-Calibrating High Dynamic Range Radiance Fields](https://mlsanity.com/paper/2208.06787/) (2022)
- [View Synthesis with Sculpted Neural Points](https://mlsanity.com/paper/2205.05869/) (2022)
- [PatchMVSNet: Patch-wise Unsupervised Multi-View Stereo for Weakly-Textured Surface Reconstruction](https://mlsanity.com/paper/2203.02156/) (2022)
- [Topology-aware Human Avatars with Semantically-guided Gaussian Splatting](https://mlsanity.com/paper/2408.09665/) (2024)

## Abstract (arXiv)

In this paper we present ADOP, a novel point-based, differentiable neural rendering pipeline. Like other neural renderers, our system takes as input calibrated camera images and a proxy geometry of the scene, in our case a point cloud. To generate a novel view, the point cloud is rasterized with learned feature vectors as colors and a deep neural network fills the remaining holes and shades each output pixel. The rasterizer renders points as one-pixel splats, which makes it very fast and allows us to compute gradients with respect to all relevant input parameters efficiently. Furthermore, our pipeline contains a fully differentiable physically-based photometric camera model, including exposure, white balance, and a camera response function. Following the idea of inverse rendering, we use our renderer to refine its input in order to reduce inconsistencies and optimize the quality of its output. In particular, we can optimize structural parameters like the camera pose, lens distortions, point positions and features, and a neural environment map, but also photometric parameters like camera response function, vignetting, and per-image exposure and white balance. Because our pipeline includes photometric parameters, e.g.~exposure and camera response function, our system can smoothly handle input images with varying exposure and white balance, and generates high-dynamic range output. We show that due to the improved input, we can achieve high render quality, also for difficult input, e.g. with imperfect camera calibrations, inaccurate proxy geometry, or varying exposure. As a result, a simpler and thus faster deep neural network is sufficient for reconstruction. In combination with the fast point rasterization, ADOP achieves real-time rendering rates even for models with well over 100M points. https://github.com/darglein/ADOP