Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo

Mehl, Lukas; Schmalfuss, Jenny; Jahedi, Azin; Nalivayko, Yaroslava; Bruhn, Andrés

doi:10.1109/cvpr52729.2023.00482

Cited by 15 publications

(2 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Next, we evaluate our MaxFlow and the SOTA methods on high-resolution images of 1080p to 2K (1,280×720 to 1,920×1,080) size. The sintel methods were further finetuned with an additional 100k iterations to enhance performance using the Spring dataset [28], which is composed of 2K images tailored for high-resolution OFE. For validation, we employ the DAVIS dataset [29], a benchmark for video segmentation that includes video sequences of 2K resolutions.…”

Section: Experiments Resultsmentioning

confidence: 99%

Lightweight Optical Flow Estimation Using 1D Matching

Seo,

Park,

Kim

2024

IEEE Access

View full text Add to dashboard Cite

Recent advancements in optical flow estimation have led to notable performance gains, driven by the adoption of transformer architectures, enhanced data augmentation, self-supervised learning techniques, the use of multiple video frames and iterative refinement of estimate optical flows. Nonetheless, these cutting-edge methods encounter substantial challenges with surge in computational complexity and memory demands. In response, we introduce a lightweight optical flow method, called MaxFlow, to address the trade-off between computational complexity and prediction performance. By leveraging MaxViT, we design a network with a global receptive field at reduced complexity, and proposed 1D matching to alleviate the computational complexity from (H ×W ) 2 to H ×W (H +W ). Consequently, our method achieves the lowest computational complexity compared to both SOTA and other lightweight optical flow estimation methods, while still achieving competitive results with the SOTA techniques. We performed extensive experiments to show the effectiveness of our method, achieving about 5 to 6× reductions in computation complexity while maintaining the prediction accuracy with only degradation of 1.61 to 1.87 in term of end point error(EPE) at Sintel test clean sequences with respect to RAFT.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Lightweight Optical Flow Estimation Using 1D Matching

Seo,

Park,

Kim

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Specifically, the rendered images of the Spring [34] dataset were used as a dataset for training and validation. The dataset consists of a total of 47 scenes and 6000 images.…”

Section: Experiments a Datasetsmentioning

confidence: 99%

TAKDSR: Teacher Assistant Knowledge Distillation Framework for Graphics Image Super-Resolution

Yoon,

Lee,

Song

2023

IEEE Access

View full text Add to dashboard Cite

This paper presents a framework for effectively applying knowledge distillation (KD) to superresolution (SR) tasks for computer graphics (CG) images. Specifically, we propose TAKDSR, a KD framework for SR using a teacher assistant (TA) network. Recently, the performance of SR models has improved dramatically thanks to the development of deep learning. SR models have evolved into a form that requires a considerable amount of computation and parameters while adopting a complex neural network structure to improve performance. However, it is difficult to utilize conventional high-performance SR models for real-time up-scaling in CG applications requiring high resolution and high frame rate. To solve this, we employ an approach that applies KD to a lightweight SR model. At this time, if the high-resolution (HR) image is used as input for the teacher to show superior performance to the student, a large performance difference occurs between the two due to the excessive performance of the teacher. As a result, the teacher's knowledge has a significantly hard and complex nature, and when transferred to the student, the effect of KD can be rather weakened. Therefore, we adopt a TA network to facilitate the propagation of knowledge between teacher and student. At the same time, the distribution of compact features (CF), which are the decoder input of the teacher, is discretized so that it is compatible with the input distribution of the student, enabling effective KD. Experimental results demonstrate the proposed TAKDSR significantly improves the performance of a given SR model on CG image datasets.

show abstract