Related papers: Deep Cost Ray Fusion for Sparse Depth Video Comple…

Deep learning-based image fusion approaches have obtained wide attention in recent years, achieving promising performance in terms of visual perception. However, the fusion module in the current deep learning-based methods suffers from two…

In video and image generation tasks, Diffusion Transformer (DiT) models incur extremely high computational costs due to attention mechanisms, which limits their practical applications. Furthermore, with hardware advancements, a wide range…

In existing self-supervised depth and ego-motion estimation methods, ego-motion estimation is usually limited to only leveraging RGB information. Recently, several methods have been proposed to further improve the accuracy of…

The size of training dataset is known to be among the most dominating aspects of training high-performance face recognition embedding model. Building a large dataset from scratch could be cumbersome and time-intensive, while combining…

The raw depth image captured by the indoor depth sensor usually has an extensive range of missing depth values due to inherent limitations such as the inability to perceive transparent objects and limited distance range. The incomplete…

Current LiDAR-only 3D detection methods inevitably suffer from the sparsity of point clouds. Many multi-modal methods are proposed to alleviate this issue, while different representations of images and point clouds make it difficult to fuse…

Depth completion is a popular research direction in the field of depth estimation. The fusion of color and depth features is the current critical challenge in this task, mainly due to the asymmetry between the rich scene details in color…

We present a method to estimate dense depth by optimizing a sparse set of points such that their diffusion into a depth map minimizes a multi-view reprojection error from RGB supervision. We optimize point positions, depths, and weights…

Convolutional neural networks have recently been used for multi-focus image fusion. However, due to the lack of labeled data for supervised training of such networks, existing methods have resorted to adding Gaussian blur in focused images…

Image fusion seeks to integrate complementary information from multiple sources into a single, superior image. While traditional methods are fast, they lack adaptability and performance. Conversely, deep learning approaches achieve…

Recently, the dense correlation volume method achieves state-of-the-art performance in optical flow. However, the correlation volume computation requires a lot of memory, which makes prediction difficult on high-resolution images. In this…

We present a novel online depth map fusion approach that learns depth map aggregation in a latent feature space. While previous fusion methods use an explicit scene representation like signed distance functions (SDFs), we propose a learned…

Multi-view depth estimation has achieved impressive performance over various benchmarks. However, almost all current multi-view systems rely on given ideal camera poses, which are unavailable in many real-world scenarios, such as autonomous…

Multi-view depth estimation plays a critical role in reconstructing and understanding the 3D world. Recent learning-based methods have made significant progress in it. However, multi-view depth estimation is fundamentally a…

Incrementally recovering 3D dense structures from monocular videos is of paramount importance since it enables various robotics and AR applications. Feature volumes have recently been shown to enable efficient and accurate incremental dense…

The integration of RGB and depth modalities significantly enhances the accuracy of segmenting complex indoor scenes, with depth data from RGB-D cameras playing a crucial role in this improvement. However, collecting an RGB-D dataset is more…

This paper proposes a depth estimation method using radar-image fusion by addressing the uncertain vertical directions of sparse radar measurements. In prior radar-image fusion work, image features are merged with the uncertain sparse…

The increasing demand to process long and high-resolution videos significantly burdens Large Vision-Language Models (LVLMs) due to the enormous number of visual tokens. Existing token reduction methods primarily prune tokens based on…

We aim at predicting a complete and high-resolution depth map from incomplete, sparse and noisy depth measurements. Existing methods handle this problem either by exploiting various regularizations on the depth maps directly or resorting to…

The deep multi-view stereo (MVS) and stereo matching approaches generally construct 3D cost volumes to regularize and regress the output depth or disparity. These methods are limited when high-resolution outputs are needed since the memory…