ETA: Energy-based Test-time Adaptation for Depth Completion
We propose a method for test-time adaptation of pretrained depth completion models. Depth completion models, trained on some `source'' data, often predict erroneous outputs when transferred to target'' data captured in novel environmental conditions due to a covariate shift. The crux of our method lies in quantifying the likelihood of depth predictions belonging to the source data distribution. The challenge is in the lack of access to out-of-distribution (target) data prior to deployment. Hence, rather than making assumptions regarding the target distribution, we utilize adversarial perturbations as a mechanism to explore the data space. This enables us to train an energy model that scores local regions of depth predictions as in- or out-of-distribution. We update the parameters of pretrained depth completion models at test time to minimize energy, effectively aligning test-time predictions to those of the source distribution. We call our method `Energy-based Test-time Adaptation'', or ETA for short. We evaluate our method across three indoor and three outdoor datasets, where ETA improve over the previous state-of-the-art method by an average of 6.94% for outdoors and 10.23% for indoors. Project Page: https://fuzzythecat.github.io/eta.
Code (0)
등록된 구현이 없습니다.
Tasks
Test-time AdaptationDepth CompletionSimilar Papers 제목 키워드 기반
Efficient Test-Time Optimization for Depth Completion via Low-Rank Decoder Adaptation
Zero-shot depth completion has gained attention for its ability to generalize across environments without sensor-specific datasets or retraining. However, most existing approaches rely on diffusion-based test-time optimi…
Test-time AdaptationDepth CompletionTest-Time Adaptation for Depth Completion
It is common to observe performance degradation when transferring models trained on some (source) datasets to target testing data due to a domain gap between them. Existing methods for bridging this gap, such as domain a…
Depth CompletionDomain AdaptationTest-time AdaptationProject to Adapt: Domain Adaptation for Depth Completion from Noisy and Sparse Sensor Data
Depth completion aims to predict a dense depth map from a sparse depth input. The acquisition of dense ground truth annotations for depth completion settings can be difficult and, at the same time, a significant domain g…
Depth CompletionDomain AdaptationTest-Time Adaptation for Height Completion via Self-Supervised ViT Features and Monocular Foundation Models
Accurate digital surface models (DSMs) are essential for many geospatial applications, including urban monitoring, environmental analyses, infrastructure management, and change detection. However, large-scale DSMs freque…
Monocular Depth EstimationTest-time AdaptationChange DetectionMetaComp: Learning to Adapt for Online Depth Completion
Relying on deep supervised or self-supervised learning, previous methods for depth completion from paired single image and sparse depth data have achieved impressive performance in recent years. However, facing a new env…
Depth CompletionMeta-LearningSelf-Supervised Learning