# DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds

arXiv: https://arxiv.org/abs/2308.04383 · HTML: https://mlsanity.com/paper/2308.04383/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 61 references that are in the map.
- First posted on arXiv 8 Aug 2023.

## Builds on (most cited first, 30 of 45)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation](https://mlsanity.com/paper/1612.00593/) (2016)
- [PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space](https://mlsanity.com/paper/1706.02413/) (2017)
- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation](https://mlsanity.com/paper/1512.02134/) (2015)
- [FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks](https://mlsanity.com/paper/1612.01925/) (2016)
- [3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction](https://mlsanity.com/paper/1604.00449/) (2016)
- [Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution](https://mlsanity.com/paper/2007.16100/) (2020)
- [Point-Voxel CNN for Efficient 3D Deep Learning](https://mlsanity.com/paper/1907.03739/) (2019)
- [OctNet: Learning Deep 3D Representations at High Resolutions](https://mlsanity.com/paper/1611.05009/) (2016)
- [FlowNet3D: Learning Scene Flow in 3D Point Clouds](https://mlsanity.com/paper/1806.01411/) (2018)
- [SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud](https://mlsanity.com/paper/1710.07368/) (2017)
- [SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud](https://mlsanity.com/paper/1809.08495/) (2018)
- [Optimal Transport for structured data with application on graphs](https://mlsanity.com/paper/1805.09114/) (2018)
- [SqueezeSegV3: Spatially-Adaptive Convolution for Efficient Point-Cloud Segmentation](https://mlsanity.com/paper/2004.01803/) (2020)
- [Hierarchical Neural Architecture Search for Deep Stereo Matching](https://mlsanity.com/paper/2010.13501/) (2020)
- [SPLATNet: Sparse Lattice Networks for Point Cloud Processing](https://mlsanity.com/paper/1802.08275/) (2018)
- [RangeDet:In Defense of Range View for LiDAR-based 3D Object Detection](https://mlsanity.com/paper/2103.10039/) (2021)
- [FLOT: Scene Flow on Point Clouds Guided by Optimal Transport](https://mlsanity.com/paper/2007.11142/) (2020)
- [RAFT-3D: Scene Flow using Rigid-Motion Embeddings](https://mlsanity.com/paper/2012.00726/) (2020)
- [MeteorNet: Deep Learning on Dynamic 3D Point Cloud Sequences](https://mlsanity.com/paper/1910.09165/) (2019)
- [HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds](https://mlsanity.com/paper/1906.05332/) (2019)
- [Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes](https://mlsanity.com/paper/2101.06085/) (2021)
- [PV-RAFT: Point-Voxel Correlation Fields for Scene Flow Estimation of Point Clouds](https://mlsanity.com/paper/2012.00987/) (2020)
- [FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation](https://mlsanity.com/paper/2011.10147/) (2020)
- [GOT: An Optimal Transport framework for Graph comparison](https://mlsanity.com/paper/1906.02085/) (2019)
- [CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation](https://mlsanity.com/paper/2111.10502/) (2021)
- [Deep Rigid Instance Scene Flow](https://mlsanity.com/paper/1904.08913/) (2019)
- [Learning to Segment Rigid Motions from Two Frames](https://mlsanity.com/paper/2101.03694/) (2021)

## Built on by (most cited first, 14 of 14)

- [DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes](https://mlsanity.com/paper/2411.11921/) (2024)
- [DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment](https://mlsanity.com/paper/2403.18274/) (2024)
- [Zero-Shot Monocular Scene Flow Estimation in the Wild](https://mlsanity.com/paper/2501.10357/) (2025)
- [Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation](https://mlsanity.com/paper/2408.00766/) (2024)
- [3DSFLabelling: Boosting 3D Scene Flow Estimation by Pseudo Auto-labelling](https://mlsanity.com/paper/2402.18146/) (2024)
- [DifFlow3D: Toward Robust Uncertainty-Aware Scene Flow Estimation with Diffusion Model](https://mlsanity.com/paper/2311.17456/) (2023)
- [PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search](https://mlsanity.com/paper/2403.15712/) (2024)
- [A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision](https://mlsanity.com/paper/2412.00623/) (2024)
- [DiffSF: Diffusion Models for Scene Flow Estimation](https://mlsanity.com/paper/2403.05327/) (2024)
- [Self-Supervised Multi-Frame Neural Scene Flow](https://mlsanity.com/paper/2403.16116/) (2024)
- [DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-temporal Fusion](https://mlsanity.com/paper/2509.06023/) (2025)
- [RegFormer++: An Efficient Large-Scale 3D LiDAR Point Registration Network with Projection-Aware 2D Transformer](https://mlsanity.com/paper/2603.14290/) (2026)
- [SF3D-RGB: Scene Flow Estimation from Monocular Camera and Sparse LiDAR](https://mlsanity.com/paper/2602.21699/) (2026)
- [Weakly Supervised Cross-Modal Learning for 4D Radar Scene Flow Estimation](https://mlsanity.com/paper/2605.18507/) (2026)

## Abstract (arXiv)

Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits feature fusion from both modalities for point-wise scene flow estimation. Previous methods rarely predict scene flow from the entire point clouds of the scene with one-time inference due to the memory inefficiency and heavy overhead from distance calculation and sorting involved in commonly used farthest point sampling, KNN, and ball query algorithms for local feature aggregation. To mitigate these issues in scene flow learning, we regularize raw points to a dense format by storing 3D coordinates in 2D grids. Unlike the sampling operation commonly used in existing works, the dense 2D representation 1) preserves most points in the given scene, 2) brings in a significant boost of efficiency, and 3) eliminates the density gap between points and pixels, allowing us to perform effective feature fusion. We also present a novel warping projection technique to alleviate the information loss problem resulting from the fact that multiple points could be mapped into one grid during projection when computing cost volume. Sufficient experiments demonstrate the efficiency and effectiveness of our method, outperforming the prior-arts on the FlyingThings3D and KITTI dataset.