Related papers: Smart-Insertion-V: Photorealistic Video Insertion …
Referring Video Object Segmentation (R-VOS) is a challenging task that aims to segment an object in a video based on a linguistic expression. Most existing R-VOS methods have a critical assumption: the object referred to must appear in the…
Virtual reality (VR) video provides an immersive 360 viewing experience to a user wearing a head-mounted display: as the user rotates his head, correspondingly different fields-of-view (FoV) of the 360 video are rendered for observation.…
Dense video captioning (DVC) aims to generate multi-sentence descriptions to elucidate the multiple events in the video, which is challenging and demands visual consistency, discoursal coherence, and linguistic diversity. Existing methods…
Visual servoing techniques guide robotic motion using visual information to accomplish manipulation tasks, requiring high precision and robustness against noise. Traditional methods often require prior knowledge and are susceptible to…
Text-driven object insertion in 3D scenes is an emerging task that enables intuitive scene editing through natural language. However, existing 2D editing-based methods often rely on spatial priors such as 2D masks or 3D bounding boxes, and…
Conventional physically based rendering (PBR) pipelines generate photorealistic images through computationally intensive light transport simulations. Although recent deep learning approaches leverage diffusion model priors with geometry…
Existing solutions to visual simultaneous localization and mapping (V-SLAM) assume that errors in feature extraction and matching are independent and identically distributed (i.i.d), but this assumption is known to not be true -- features…
Recent Video Large Language Models (Video-LLMs) have shown strong multimodal reasoning capabilities, yet remain challenged by video understanding tasks that require consistent temporal ordering and causal coherence. Many parameter-efficient…
Creating novel images by fusing visual cues from multiple sources is a fundamental yet underexplored problem in image-to-image generation, with broad applications in artistic creation, virtual reality and visual media. Existing methods…
Video personalization aims to generate videos that faithfully reflect a user-provided subject while following a text prompt. However, existing approaches often rely on heavy video-based finetuning or large-scale video datasets, which impose…
Robust efficient loop closure detection is essential for large-scale real-time SLAM. In this paper, we propose a novel unsupervised deep neural network architecture of a feature embedding for visual loop closure that is both reliable and…
This paper addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. The two streams of the network encode spatial and temporal…
Multimodal Large Language Models (MLLMs) often struggle to accurately perceive fine-grained visual details, especially when targets are tiny or visually subtle. This challenge can be addressed through semantic-visual information fusion,…
Zero-shot scene understanding in real-world settings presents major challenges due to the complexity and variability of natural scenes, where models must recognize new objects, actions, and contexts without prior labeled examples. This work…
In this paper, we introduce a new problem of manipulating a given video by inserting other videos into it. Our main task is, given an object video and a scene video, to insert the object video at a user-specified location in the scene video…
With the explosive growth of video data in real-world applications, a comprehensive representation of videos becomes increasingly important. In this paper, we address the problem of video scene recognition, whose goal is to learn a…
Existing two-stream models, such as CLIP, encode images and text through independent representations, showing good performance while ensuring retrieval speed, have attracted attention from industry and academia. However, the single…
We present a training-free framework for occluded text rendering with a pretrained FLUX.1-dev backbone. The task requires a model to render recognizable typography and place an occluding object over the intended text region. This setting…
Humans understand and interact with the real world by relying on diverse physical feedback beyond visual perception. Motivated by this, recent approaches attempt to incorporate physical sensory signals into Vision-Language-Action models…
Different from Visual Question Answering task that requires to answer only one question about an image, Visual Dialogue involves multiple questions which cover a broad range of visual content that could be related to any objects,…