Related papers: IA-MVS: Instance-Focused Adaptive Depth Sampling f…
Depth-aware video panoptic segmentation tackles the inverse projection problem of restoring panoptic 3D point clouds from video sequences, where the 3D points are augmented with semantic classes and temporally consistent instance…
Traditional monocular Visual-Inertial Odometry (VIO) systems struggle in low-texture environments where sparse visual features are insufficient for accurate pose estimation. To address this, dense Monocular Depth Estimation (MDE) has been…
Visual Prompt Tuning (VPT) has emerged as a parameter-efficient fine-tuning paradigm for vision transformers, with conventional approaches utilizing dataset-level prompts that remain the same across all input instances. We observe that this…
Existing learning-based multi-view stereo (MVS) methods rely on the depth range to build the 3D cost volume and may fail when the range is too large or unreliable. To address this problem, we propose a disparity-based MVS method based on…
3D reconstruction has lately attracted increasing attention due to its wide application in many areas, such as autonomous driving, robotics and virtual reality. As a dominant technique in artificial intelligence, deep learning has been…
We present a visual-inertial depth estimation pipeline that integrates monocular depth estimation and visual-inertial odometry to produce dense depth estimates with metric scale. Our approach performs global scale and shift alignment…
Self-supervised monocular depth estimation (SSMDE) has gained attention in the field of deep learning as it estimates depth without requiring ground truth depth maps. This approach typically uses a photometric consistency loss between a…
Conventional 3D instance segmentation methods rely on labor-intensive 3D annotations for supervised training, which limits their scalability and generalization to novel objects. Recent approaches leverage multi-view 2D masks from the…
Molecular dynamics (MD) simulations have been widely applied to study macromolecules including proteins. However, high-dimensionality of the datasets produced by simulations makes it difficult for thorough analysis, and further hinders a…
Self-supervised depth estimation algorithms rely heavily on frame-warping relationships, exhibiting substantial performance degradation when applied in challenging circumstances, such as low-visibility and nighttime scenarios with varying…
Irregularly sampled time series (ISTS) are widespread in real-world scenarios, exhibiting asynchronous observations on uneven time intervals across variables. Existing ISTS forecasting methods often solely utilize historical observations to…
Multi-view diffusion models have shown promise in 3D novel view synthesis, but most existing methods adopt a non-autoregressive formulation. This limits their applicability in world modeling, as they only support a fixed number of views and…
Monocular depth estimation (MDE), inferring pixel-level depths in single RGB images from a monocular camera, plays a crucial and pivotal role in a variety of AI applications demanding a three-dimensional (3D) topographical scene. In the…
Subsampling is a widely used and effective approach for addressing the computational challenges posed by massive datasets. Substantial progress has been made in developing non-uniform, probability-based subsampling schemes that prioritize…
We describe a new algorithm, VEGAS+, for adaptive multidimensional Monte Carlo integration. The new algorithm adds a second adaptive strategy, adaptive stratified sampling, to the adaptive importance sampling that is the basis for its…
We consider an interactive multiview video streaming (IMVS) system where clients select their preferred viewpoint in a given navigation window. To provide high quality IMVS, many high quality views should be transmitted to the clients.…
Generating multi-view images from human instructions is crucial for 3D content creation. The primary challenges involve maintaining consistency across multiple views and effectively synthesizing shapes and textures under diverse conditions.…
Stereo matching plays a crucial role in 3D perception and scenario understanding. Despite the proliferation of promising methods, addressing texture-less and texture-repetitive conditions remains challenging due to the insufficient…
Multi-view clustering (MvC) utilizes information from multiple views to uncover the underlying structures of data. Despite significant advancements in MvC, mitigating the impact of missing samples in specific views on the integration of…
One of the common algorithms used to reconstruct photoacoustic (PA) images is the non-adaptive Delay-and-Sum (DAS) beamformer. However, the quality of the reconstructed PA images obtained by DAS is not satisfying due to its high level of…