Self-SuperFlow: Self-supervised Scene Flow Prediction in Stereo Sequences
In recent years, deep neural networks showed their exceeding capabilities in addressing many computer vision tasks including scene flow prediction. However, most of the advances are dependent on the availability of a vast amount of dense per pixel ground truth annotations, which are very difficult to obtain for real life scenarios. Therefore, synthetic data is often relied upon for supervision, resulting in a representation gap between the training and test data. Even though a great quantity of unlabeled real world data is available, there is a huge lack in self-supervised methods for scene flow prediction. Hence, we explore the extension of a self-supervised loss based on the Census transform and occlusion-aware bidirectional displacements for the problem of scene flow prediction. Regarding the KITTI scene flow benchmark, our method outperforms the corresponding supervised pre-training of the same network and shows improved generalization capabilities while achieving much faster convergence.
Code (0)
등록된 구현이 없습니다.
Tasks
PredictionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
SuperFlow++: Enhanced Spatiotemporal Consistency for Cross-Modal Data Pretraining
LiDAR representation learning has emerged as a promising approach to reducing reliance on costly and labor-intensive human annotations. While existing methods primarily focus on spatial alignment between LiDAR and camera…
Autonomous DrivingComputational EfficiencyContrastive LearningRepresentation Learning+1SuperFlow: Training Flow Matching Models with RL on the Fly
Recent progress in flow-based generative models and reinforcement learning (RL) has improved text-image alignment and visual quality. However, current RL training for flow models still has two main problems: (i) GRPO-sty…
Reinforcement LearningImage GenerationRigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior
In this work, we focus on scene flow learning on point clouds in a self-supervised manner. A real-world scene can be well modeled as a collection of rigidly moving parts, therefore its scene flow can be represented a…
Motion EstimationSelf-Supervised LearningSelf-Supervised Learning of Non-Rigid Residual Flow and Ego-Motion
Most of the current scene flow methods choose to model scene flow as a per point translation vector without differentiating between static and dynamic components of 3D motion. In this work we present an alternative metho…
Self-Supervised LearningTranslationJust Go with the Flow: Self-Supervised Scene Flow Estimation
When interacting with highly dynamic environments, scene flow allows autonomous systems to reason about the non-rigid motion of multiple independent objects. This is of particular interest in the field of autonomous driv…
Autonomous DrivingScene Flow EstimationSelf-supervised Scene Flow Estimation