Improved Point Transformation Methods For Self-Supervised Depth Prediction
Given stereo or egomotion image pairs, a popular and successful method for unsupervised learning of monocular depth estimation is to measure the quality of image reconstructions resulting from the learned depth predictions. Continued research has improved the overall approach in recent years, yet the common framework still suffers from several important limitations, particularly when dealing with points occluded after transformation to a novel viewpoint. While prior work has addressed this problem heuristically, this paper introduces a z-buffering algorithm that correctly and efficiently handles occluded points. Because our algorithm is implemented with operators typical of machine learning libraries, it can be incorporated into any existing unsupervised depth learning framework with automatic support for differentiation. Additionally, because points having negative depth after transformation often signify erroneously shallow depth predictions, we introduce a loss function to penalize this undesirable behavior explicitly. Experimental results on the KITTI data set show that the z-buffer and negative depth loss both improve the performance of a state of the art depth-prediction network.
Code (1)
Tasks
Depth EstimationDepth PredictionMonocular Depth EstimationPredictionSimilar Papers 제목 키워드 기반
Test-Time Personalization with a Transformer for Human Pose Estimation
We propose to personalize a human pose estimator given a set of test images of a person without using any manual annotations. While there is a significant advancement in human pose estimation, it is still very challengin…
Pose EstimationDualContrast: Unsupervised Disentangling of Content and Transformations with Implicit Parameterization
Unsupervised disentanglement of content and transformation has recently drawn much research, given their efficacy in solving downstream unsupervised tasks like clustering, alignment, and shape analysis. This problem is p…
Data AugmentationDisentanglementSelf-Consistent Recursive Diffusion Bridge for Medical Image Translation
Denoising diffusion models (DDM) have gained recent traction in medical image translation given improved training stability over adversarial models. DDMs learn a multi-step denoising transformation to progressively map r…
DenoisingSchedulingTranslationA Revisit of the Normalized Eight-Point Algorithm and A Self-Supervised Deep Solution
The normalized eight-point algorithm has been widely viewed as the cornerstone in two-view geometry computation, where the seminal Hartley's normalization has greatly improved the performance of the direct linear transfo…
Self-Supervised LearningPseudoNeg-MAE: Self-Supervised Point Cloud Learning using Conditional Pseudo-Negative Embeddings
We propose PseudoNeg-MAE, a novel self-supervised learning framework that enhances global feature representation of point cloud masked autoencoder by making them both discriminative and sensitive to transformations. Trad…
Contrastive LearningPose EstimationSelf-Supervised Learning