# FlowNet3D++: Geometric Losses For Deep Scene Flow Estimation

arXiv: https://arxiv.org/abs/1912.01438 · HTML: https://mlsanity.com/paper/1912.01438/

## Key facts

- Cited by 55 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2019.

## Built on by (most cited first, 30 of 55)

- [Shape of Motion: 4D Reconstruction from a Single Video](https://mlsanity.com/paper/2407.13764/) (2024)
- [SpatialTracker: Tracking Any 2D Pixels in 3D Space](https://mlsanity.com/paper/2404.04319/) (2024)
- [4DComplete: Non-Rigid Motion Estimation Beyond the Observable Surface](https://mlsanity.com/paper/2105.01905/) (2021)
- [Neural Scene Flow Prior](https://mlsanity.com/paper/2111.01253/) (2021)
- [TAPIP3D: Tracking Any Point in Persistent 3D Geometry](https://mlsanity.com/paper/2504.14717/) (2025)
- [DELTA: Dense Efficient Long-range 3D Tracking for any video](https://mlsanity.com/paper/2410.24211/) (2024)
- [Weakly Supervised Learning of Rigid 3D Scene Flow](https://mlsanity.com/paper/2102.08945/) (2021)
- [Motion Inspired Unsupervised Perception and Prediction in Autonomous Driving](https://mlsanity.com/paper/2210.08061/) (2022)
- [CamLiFlow: Bidirectional Camera-LiDAR Fusion for Joint Optical Flow and Scene Flow Estimation](https://mlsanity.com/paper/2111.10502/) (2021)
- [Scalable Scene Flow from Point Clouds in the Real World](https://mlsanity.com/paper/2103.01306/) (2021)
- [MultiBodySync: Multi-Body Segmentation and Motion Estimation via 3D Scan Synchronization](https://mlsanity.com/paper/2101.06605/) (2021)
- [Fast Neural Scene Flow](https://mlsanity.com/paper/2304.09121/) (2023)
- [Hidden Gems: 4D Radar Scene Flow Learning Using Cross-Modal Supervision](https://mlsanity.com/paper/2303.00462/) (2023)
- [ICP-Flow: LiDAR Scene Flow Estimation with ICP](https://mlsanity.com/paper/2402.17351/) (2024)
- [FESTA: Flow Estimation via Spatial-Temporal Attention for Scene Point Clouds](https://mlsanity.com/paper/2104.00798/) (2021)
- [Self-Supervised Multi-Frame Monocular Scene Flow](https://mlsanity.com/paper/2105.02216/) (2021)
- [Self-Supervised Scene Flow Estimation with 4-D Automotive Radar](https://mlsanity.com/paper/2203.01137/) (2022)
- [Recent Trends in 3D Reconstruction of General Non-Rigid Scenes](https://mlsanity.com/paper/2403.15064/) (2024)
- [OcclusionFusion: Occlusion-aware Motion Estimation for Real-time Dynamic 3D Reconstruction](https://mlsanity.com/paper/2203.07977/) (2022)
- [Self-Supervised 3D Scene Flow Estimation Guided by Superpoints](https://mlsanity.com/paper/2305.02528/) (2023)
- [SCTN: Sparse Convolution-Transformer Network for Scene Flow Estimation](https://mlsanity.com/paper/2105.04447/) (2021)
- [Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Stream](https://mlsanity.com/paper/2304.03184/) (2023)
- [milliFlow: Scene Flow Estimation on mmWave Radar Point Cloud for Human Motion Sensing](https://mlsanity.com/paper/2306.17010/) (2023)
- [3D Object Detection with a Self-supervised Lidar Scene Flow Backbone](https://mlsanity.com/paper/2205.00705/) (2022)
- [DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos](https://mlsanity.com/paper/2506.09997/) (2025)
- [GMSF: Global Matching Scene Flow](https://mlsanity.com/paper/2305.17432/) (2023)
- [Multi-Body Neural Scene Flow](https://mlsanity.com/paper/2310.10301/) (2023)
- [Match Stereo Videos via Bidirectional Alignment](https://mlsanity.com/paper/2409.20283/) (2024)
- [Learning Optical Flow and Scene Flow with Bidirectional Camera-LiDAR Fusion](https://mlsanity.com/paper/2303.12017/) (2023)
- [DELTAv2: Accelerating Dense 3D Tracking](https://mlsanity.com/paper/2508.01170/) (2025)

## Abstract (arXiv)

We present FlowNet3D++, a deep scene flow estimation network. Inspired by classical methods, FlowNet3D++ incorporates geometric constraints in the form of point-to-plane distance and angular alignment between individual vectors in the flow field, into FlowNet3D. We demonstrate that the addition of these geometric loss terms improves the previous state-of-art FlowNet3D accuracy from 57.85% to 63.43%. To further demonstrate the effectiveness of our geometric constraints, we propose a benchmark for flow estimation on the task of dynamic 3D reconstruction, thus providing a more holistic and practical measure of performance than the breakdown of individual metrics previously used to evaluate scene flow. This is made possible through the contribution of a novel pipeline to integrate point-based scene flow predictions into a global dense volume. FlowNet3D++ achieves up to a 15.0% reduction in reconstruction error over FlowNet3D, and up to a 35.2% improvement over KillingFusion alone. We will release our scene flow estimation code later.