Related papers: Point2Insert: Video Object Insertion via Sparse Po…
Diffusion-based inpainting is a powerful tool for the reconstruction of images from sparse data. Its quality strongly depends on the choice of known data. Optimising their spatial location -- the inpainting mask -- is challenging. A…
Point cloud-based open-vocabulary 3D object detection aims to detect 3D categories that do not have ground-truth annotations in the training set. It is extremely challenging because of the limited data and annotations (bounding boxes with…
Video Instance Segmentation is a fundamental computer vision task that deals with segmenting and tracking object instances across a video sequence. Most existing methods typically accomplish this task by employing a multi-stage top-down…
Segmenting unknown or anomalous object instances is a critical task in autonomous driving applications, and it is approached traditionally as a per-pixel classification problem. However, reasoning individually about each pixel without…
Referring video object segmentation (RVOS) aims to segment objects in a video according to textual descriptions, which requires the integration of multimodal information and temporal dynamics perception. The Segment Anything Model 2 (SAM 2)…
Object detection in videos is an important task in computer vision for various applications such as object tracking, video summarization and video search. Although great progress has been made in improving the accuracy of object detection…
We present Lang2Motion, a framework for language-guided point trajectory generation by aligning motion manifolds with joint embedding spaces. Unlike prior work focusing on human motion or video synthesis, we generate explicit trajectories…
Recently, the self-supervised learning framework data2vec has shown inspiring performance for various modalities using a masked student-teacher approach. However, it remains open whether such a framework generalizes to the unique challenges…
Recommender systems often rely on large embedding tables that map users and items to dense vectors of uniform size, leading to substantial memory consumption and inefficiencies. This is particularly problematic in memory-constrained…
Creating animatable avatars from static scans requires the modeling of clothing deformations in different poses. Existing learning-based methods typically add pose-dependent deformations upon a minimally-clothed mesh template or a learned…
Recent image-to-video (I2V) based video inpainting methods have made significant strides by leveraging single-image priors and modeling temporal consistency across masked frames. Nevertheless, these methods suffer from severe content…
Existing 3D instance segmentation methods frequently encounter issues with over-segmentation, leading to redundant and inaccurate 3D proposals that complicate downstream tasks. This challenge arises from their unsupervised merging approach,…
Current 3D segmentation methods heavily rely on large-scale point-cloud datasets, which are notoriously laborious to annotate. Few attempts have been made to circumvent the need for dense per-point annotations. In this work, we look at…
Video inpainting involves modifying local regions within a video, ensuring spatial and temporal consistency. Most existing methods focus primarily on scene completion (i.e., filling missing regions) and lack the capability to insert new…
Small object-centric spatial understanding in indoor videos remains a significant challenge for multimodal large language models (MLLMs), despite its practical value for object search and assistive applications. Although existing benchmarks…
Weakly Supervised Object Localization (WSOL), which aims to localize objects by only using image-level labels, has attracted much attention because of its low annotation cost in real applications. Current studies focus on the Class…
This work proposes a process for efficiently training a point-wise object detector that enables localizing objects and computing their 6D poses in cluttered and occluded scenes. Accurate pose estimation is typically a requirement for robust…
Camera and object motions are central to a video's narrative. However, precisely editing these captured motions remains a significant challenge, especially under complex object movements. Current motion-controlled image-to-video (I2V)…
Video instance segmentation (VIS) is a challenging vision task that aims to detect, segment, and track objects in videos. Conventional VIS methods rely on densely-annotated object masks which are expensive. We reduce the human annotations…
Complex video object segmentation serves as a fundamental task for a wide range of downstream applications such as video editing and automatic data annotation. Here we present the 2nd place solution in the MOSE track of PVUW 2024. To…